Podcasts about Confluence

History is rhyming. The last time dividend stocks were this out of favor, the dot-com bubble was peaking. Portfolio Manager Tom Dugan joins Director of RIA Relationships Emily D'Agostino to discuss why that dynamic looks a lot like 1999, what the historical data says about what comes next, and why the Confluence IDEA strategy's quarter-century of consistent philosophy and construction may be precisely what this moment calls for. If history is any guide, patient investors may be about to be rewarded.

On this date in 1929, Joseph Blanding was still living in the family farmhouse at the south end of Wahpeton. He gave a talk to the Wilkin County Historical Society that was later published in the local paper. Joseph came to the area in 1872 at age nine, before Wahpeton was settled.

I had a blast chatting with Sherif Mansour, Head of AI at Atlassian, at Team '26 in Anaheim. If you want to understand what Atlassian actually shipped this year and why it matters, this is the conversation to watch.Sherif is the person inside Atlassian who has been thinking about AI longest and hardest. He runs Atlassian Intelligence, the generative AI platform that powers Rovo, the Teamwork Graph, and the agent experiences across Jira, Confluence, and Loom. When the entire company stage talks about AI for two hours, Sherif is one of the people who actually built what they are talking about.That made this conversation different from most AI interviews you will hear this year.What we covered:The keynote in his own words. Atlassian announced AI for developers, service teams, product teams, agents in Jira, and a brand new Product Collection. I asked Sherif what excites him most across all of it. His answer surprised me.Teamwork Graph, opened up. The 150 billion connection graph is now accessible to any agent through MCP, CLI, and Forge connectors. I asked Sherif what "opening it up" actually means in practice, and what changes for builders outside Atlassian who want to plug in.Agent orchestration in Jira. What it looks like when an agent is not just answering questions but coordinating work across an entire project. Sherif walked through how Atlassian thinks about keeping humans in the loop where it matters, and where to get out of the way.AI mythbusting. Sherif came in with strong opinions on the myths he is tired of hearing. We spent real time here. If you work in or around enterprise AI, this section alone is worth the watch.The line that stayed with me: the hardest problem in enterprise AI is not making models smarter. It is making them aware of how your company actually works. Everything Atlassian shipped at Team '26 traces back to that one bet.Big thank you to Sherif for the depth, the candor, and the patience with my follow-up questions. And to the Atlassian team for the front-row access at Team '26.#data #ai #atlassian #team26 #theravitshow

Join this channel to get access to perks: https://www.youtube.com/channel/UCVr5MNf7Nt5oCXywsUh-ttA/join   Looking to buy used and new games?  Use my affiliate link  with Noble Knight Games https://www.nobleknight.com/?awid=1459   Hungry is joined by Don from the Secret Cabal and Original Don his Occasional Regular Co-host in a Confluence of Donnery.   0:00 - Intro Recent Plays 2:56 - Moytura 7:34 - Aelderman 11:37 - Oathsworn 17:28 - Tigris and Euphrates 23:33 - Faerie Ring 26:20 - Gunsen: Battle for Toshii Ranbo 33:43 - Beast: Shattered Isles Shelf of Shame Games 40:47 - Free Radicals 44:07 - Black Rose Wars 46:20 - Tales from the Red Dragon Inn 47:36 - Fateforge 52:58 - Soul Raiders 54:50 - Maria 1:00:54 - Sweet Lands 1:32:29 - Old Games We are want to get back to the table Check out the video version here: https://youtu.be/mbn78tikwQw Check out Secret Cabal here: https://thesecretcabal.com/ Check out Backyard Chickens here: https://backyard-chickens.backerkit.com/hosted_preorders/

What if agentic AI makes SRE more important, not less? Bennett Gould explains why autonomous AI systems may create more demand for reliability thinking — not less.Everyone seems to think AI is coming for SRE in a hard way.You might have heard the same story:“AI will write the code.”“Agents will handle incidents.”“Copilots will generate the runbooks.”“Automation will reduce operational load.”Yes, the job question is real. If AI can write code, summarize incidents, query observability tools, generate runbooks, and operate across systems, then engineers are right to ask what happens to the work.But here's the part that gets missed: AI does not just automate reliability work. It creates more objects and surface areas that need to be made reliable.Agentic AI is moving from demos into real workflows. These systems are no longer just answering questions. They are querying tools, pulling context, generating changes, and in some cases taking action around production environments.That makes this a Monday morning problem.Teams are already using LLMs for incidents, documentation, observability, infrastructure, and operational decision-making. Somewhere, a team is one demo away from giving an agent access to tools originally designed for humans.That is exactly why I wanted to have this conversation.Bennett Gould is currently a solution engineer at Neubird.ai. His career in SRE and SRE-adjacent work spans large enterprises, cloud, industrial technology, and startups, including AWS, IBM, Siemens, and a YC startup.I wanted to ask him a simple question: What in the agentic AI is happening to SRE?Here are 3 highlights from our talk:1. Agentic AI increases the reliability surface areaThe obvious fear is that AI reduces the need for reliability engineers. Bennett's view was more nuanced. He was clear that engineers still need to adapt. If people do not reskill, stay current, and learn how these systems are forming, there may absolutely be pressure in the job market. But he also argued that AI could create more demand for reliability skills because production complexity is increasing.More code is going into production.More AI-generated code is going into production.More systems that people do not fully understand are going into production.And now autonomous agents are starting to enter production workflows too.That means more surface area. More automation. More operational uncertainty. More ways for things to go wrong.Bennett compared this to Terraform: Infrastructure as code created enormous efficiency gains. But it also created new ways to make very big mistakes very quickly.Before Terraform, most people could not delete all their production resources with a single command. After Terraform, that became technically possible if the system was designed badly enough.Agentic AI follows a similar pattern. With great automation comes great responsibility.Agents can help engineers move faster, query tools, summarize context, and reduce toil. But they can also amplify weak engineering practices, poor boundaries, bad assumptions, and unclear operational ownership. That is not the end of reliability work. That is reliability work entering a new phase.2. Agents can reduce toil, but context is the ceilingOne of the strongest parts of the conversation was Bennett's explanation of where agents can help in incident response. A lot of SRE work involves moving across tools.You may need to query Prometheus, Dynatrace, logs, traces, cloud consoles, ticketing systems, documentation, runbooks, dashboards, and architecture diagrams.The problem is not always that the engineer lacks judgment.Sometimes the problem is that the information is scattered across too many tools, each with its own query language and interface. Bennett gave a simple example: an engineer might be very good at PromQL and very fast when Prometheus is the source of truth. But if the same engineer has to work in a different observability platform with a different query language, their response time can suffer. That is an obvious place where agents can help.The engineer may not need to know every query language perfectly. They need to know what they are looking for and how to reason about the system. The agent can help translate that intent into the right tool calls, queries, and summaries.That could reduce MTTR. It could reduce toil. It could help engineers move faster during incidents.But Bennett also made the limitation clear: You are only as good as the context you have. This is where he introduced two useful concepts:* Context mining* Context distillationContext mining means proactively finding the information that might be useful in a given operational situation.Context distillation means taking large amounts of information — runbooks, Confluence pages, diagrams, documentation, prior incidents — and reducing it into the minimum useful context an LLM or agent can use.That sounds powerful. But there is a catch. Sometimes the context simply is not there.Many of the largest and most complex organizations still run legacy systems where knowledge lives in people's heads, stale documentation, tribal memory, and unwritten assumptions.There may not be a clean process for turning that into usable context. That matters because agents do not magically understand your system. They work with the context they are given. If the context is missing, outdated, or wrong, the agent's usefulness maxes out early.3. Agentic systems are not just LLM demosA basic LLM workflow is relatively easy to demo:You give it a prompt.You connect a few tools.You add some APIs.You get a useful answer.That is impressive, but it is not the same thing as running an agentic system in a meaningful production environment.Bennett made a useful analogy here: running your own infrastructure versus using a hyperscaler.Cloud providers removed a lot of undifferentiated heavy lifting. Most companies do not want to spend half their time racking servers, managing data centers, and dealing with low-level infrastructure when they are trying to serve customers.Agentic systems create similar questions:* What parts of the work should be handled by the system?* What parts still need engineering discipline?* And what has to exist around the model before it is safe and useful?That surrounding structure is where the real work begins. Bennett called this harness engineering. Once you move beyond an LLM demo, you have to think about memory, learning, tool usage, identity, federation, security, evaluations, and guardrails.That is a very different problem from “the model gave a good answer on my laptop.” SREs know why that distinction matters. “It works on my machine” is not an acceptable reliability strategy.A runbook that recovers a thousand-node database cannot be non-deterministic, undocumented, and dependent on someone's local setup. If it is part of the operational backbone, it needs to be reliable.Agentic AI does not remove that requirement. It makes it more important.Bonus: Agents expose weak engineering practicesAgentic AI not only introduces new problems but it also reveals old ones.* Weak APIs.* Brittle runbooks.* Missing context.* Poor evals.* Unclear tool boundaries.* Operational shortcuts.Systems that were designed assuming careful human use may behave very differently when AI agents start using them. That is why this conversation matters for SRE.Agentic AI is not only a productivity story. It is a reliability story.It forces teams to ask whether their existing practices are strong enough for a world where more actions can be generated, recommended, or executed by autonomous systems.The silver lining for reliability workAgentic AI does not remove the need for reliability thinking. It raises the bar for it. The tools will change. The workflows will change. Some tasks will absolutely be automated or reshaped.But the hardest parts of reliability are still the hard parts:* understanding the system* knowing the trade-offs* building reliable operational processes* making good judgment calls under uncertainty and* owning the outcome when something changes in productionThat is why SRE does not disappear in an agentic AI world.It becomes one of the disciplines that makes the agentic AI world survivable.So if your team is already using AI around incidents, observability, runbooks, infrastructure, or production workflows, the question is not whether the future is coming. The future is already in the workflow.The real question is whether your reliability practices are ready for it. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit read.srepath.com

This episode features Jane Reasoner and Abbey Eckberg of Confluence discussing new research on the potential for missing middle housing in Central Iowa. Get session descriptions and slides speakers shared at https://www.pchtf.org/post/reflections-on-housing-matters-symposium-2026

How does a program built around relationships, adventure, and the outdoors evolve over ten years while staying true to its mission? In this episode, Will sits down with Foster Post, co-founder of Confluence Behavioral Health, as the Vermont-based program celebrates its 10th anniversary. Foster shares his journey into outdoor mental health treatment and reflects on the lessons learned from building a small, owner-operated program during a time of unprecedented change. From its early years featuring multi-day wilderness expeditions to its current model serving young adults through residential treatment, adventure-based programming, and community engagement, Confluence has continually adapted while staying true to its core belief in the healing power of relationships and the outdoors. Foster and Will also explore the changing needs of young adults, including rising anxiety, social isolation, self-doubt, and the impact of technology on mental health. Together, they discuss how outdoor behavioral healthcare is evolving, why community and experiential learning remain essential for growth, and what the future may hold for nature-based treatment programs. This conversation offers valuable insights for parents, clinicians, educational consultants, and anyone interested in young adult mental health, outdoor therapy, and the future of behavioral healthcare. This podcast is supported by White Mountain Adventure Institute (wmai.org), offering adventure inspired retreats and coaching facilitated by Will White.

BONUS: The Communication Tax — Why Your Team Collaborates Too Much and What to Cut First In this BONUS episode, Roman Nikolaev challenges one of the most deeply held beliefs in the agile world: that more collaboration is always better. As Head of Technology at Cambri, Roman has watched teams burn their best hours in meetings and handoffs that create the feeling of productivity without the outcomes. He shares practical tools — from the vacation test to RFC processes — that help teams find the minimum viable level of collaboration. From Senior Engineer to Accidental Manager "I kind of accidentally ended up in management. I didn't want to lead anyone, I wanted to be just a senior engineer doing my stuff. But somehow, four months in the job, I was already leading a team, and then one year after, I was head of technology."   Roman's career in engineering goes back to the early 2000s. When he changed jobs during COVID, he specifically didn't want a management role — he wanted to code. But within months he was leading a team, and within a year he was running the entire technical organization at Cambri. That unexpected shift from hands-on engineering to leading teams gave him a front-row seat to how collaboration actually works — and how often it doesn't. What he noticed was that the most important differentiator for technical teams isn't technical knowledge — it's communication, and the tax you pay when communication goes wrong. The Communication Tax Is Real "The communication tax is real. The less we need to pay for communication, the more we can concentrate and own things end to end."   Roman describes a pattern most teams will recognize: stakeholders inside and outside the team — product managers, QA, scrum masters, product owners — and at some point, it becomes a game of telephone. The people doing the actual work don't have the context they need. The result? Unnecessary features, wrong implementations, suboptimal technical solutions that don't scale. His argument isn't that collaboration is bad. It's that every handoff, every meeting, every "quick sync" has a cost — and most teams aren't honest about how much they're paying. Handoffs Aren't Collaboration "If you look at a typical software development lifecycle — a ticket created by a product owner, refinement with the team, development, code review, QA, acceptance — there are quite many handoffs. If we can reduce some of this, we get a more effective workflow."   Roman walks through the standard ticket lifecycle and counts the handoffs: PO creates ticket, team refines, developer picks it up, code review with other developers, QA phase, acceptance phase. Each transition is a potential information loss. His provocation: instead of involving more people when someone struggles with a task, give the person working on it the tools and knowledge to complete it independently. The trigger for his thinking was a real team conversation where someone suggested everyone should "jump on the ticket" to help. Roman's response: wouldn't it be better to equip the individual rather than create more dependencies? Async Tools That Actually Work "Instead of gathering a meeting where people come unprepared or with some raw ideas, we have ownership for a task. Someone takes their time, writes down their thoughts, options in a document, and then we assign people to review it."   Roman shares two async practices his teams use at Cambri. First, the RFC (Request for Comments) process on Confluence — one person owns a decision, writes it up with options, and assigned reviewers sign off asynchronously. It turns out to be more effective at finding better technical solutions while spreading knowledge without requiring synchronous deep-dives. Second, his Monday written updates: every week, he spends about 90 minutes writing a detailed post covering all project statuses, what happened last week, what's coming, and business context. The team feedback in skip-level meetings is consistently positive, and he fields far fewer questions about business context and priorities than before the practice started. The Vacation Test "One heuristic would be that if one of the team members goes on vacation, the rest of the team can continue working on their task."   Roman learned this the hard way. He went on a typical Finnish one-month vacation. Before leaving, he explained the architecture and intent for a key task to his team. He came back to discover they'd built the completely wrong thing — wasting one month of a two-month project. He spent the remaining time working weekends, on planes, on trains, just to hit the deadline. The lesson wasn't that he needed more collaboration or synchronous communication before leaving. It was that he needed better communication — and a way to test whether shared context actually exists. His heuristic: if Alice goes on vacation, can Bob continue from where she stopped? If not, you don't need more meetings. You need better async context-sharing. Where to Start: Ownership First, Then Cut Meetings "I would probably first look into if a particular initiative, a feature, or some kind of process has an owner and well-defined roles. Usually, if there is no clear owner, that leads to a lot of synchronous meetings."   For Scrum Masters and team leads looking for a practical starting point, Roman offers a two-step approach. First, ensure every initiative, feature, and process has a clear owner with well-defined roles. Without clear ownership, meetings multiply because nobody is sure who's responsible, so everyone attends everything. Second, look at the team calendar starting with the biggest meetings and ask: can this be an RFC? A message? An email? Then experiment — cancel a meeting, replace it with an async channel, and see what happens. You can always bring it back. In the agile world, Roman argues, we should embrace experimentation with our own processes, not just our products. Recommended Resources Roman recommends Team Topologies by Matthew Skelton and Manuel Pais. The book gave him a clear mental model for independent teams that own their area end to end — teams aligned to value streams that own the customer problem completely. For more of Roman's thinking on collaboration, check out his Substack newsletter: Is Your Collaboration Good or Evil? on High Impact Engineering. About Roman Nikolaev Roman Nikolaev is Head of Technology at Cambri. He's spent his career thinking about how teams actually get work done — and his contrarian view that most teams collaborate too much has sparked real debate in the agile community.   You can link with Roman Nikolaev on LinkedIn.

Our latest podcast features Joseph Lubin, Co-Founder of Ethereum and Founder and CEO of Consensys, in conversation with Manish Kohli, Head of Global Payments Solutions, HSBC. They explore how decentralised trust, tokenisation and smart contracts are reshaping finance, from stablecoins and tokenised deposits to real-world assets with digital twins.Watch or listen to find out more.This episode was recorded on the sidelines of the HSBC Global Investment Summit 2026 in Hong Kong. Find out more https://www.business.hsbc.com/en-gb/campaigns/global-investment-summitDisclaimer: Views of external guest speakers do not represent those of HSBC.

In this episode of Liminal Phrames, Darren/Exo and Nathan go where the current societal conversation around UFOs and NHI has yet to go: into questions around the abduction and hybridization phenomenon. What's happening, and how is it more complex and multifaceted than most people are ready to metabolize?

Researcher, artist, and curator Pietro Consolandi traces the ‘wetland turn' in art, ecology, and environmental justice, via Giovanni Pellegrini's 2025 documentary film, The Venice Lagoon, a legal person.Nature Speaks: Listening for Rights of Nature in Venice and Europe is at Ocean Space in Venice until 11 October 2026. The Research Unit, curated by Pietro Consolandi and Amalia Rossi, is co-produced by TBA21–Academy and NICHE Centre for Environmental Humanities, Ca' Foscari University of Venice, in collaboration with IDRA (Initiative for the Rights of Water) and the Confluence of European Water Bodies. You can join the next Citizens' Assembly for the Rights of the Lagoon on 10 October 2026.The Venice Lagoon, a legal person (2025) is available to watch online.For more about water bodies in Europe, hear Klima Biennale Wien festival director Sithara Pathirana on climate justice, public space and the rights of the river Danube through Austria, Central, Eastern, and Southeastern Europe, in the episode about Superflux's sculptural installation, Nobody Told Me Rivers Dream (2025): pod.link/1533637675/episode/ZWQ4Mzg0Y2MtMWFkMy00ZmJkLWIyZjUtNGU3MmJmODM2ODExOn the flows between Wales and Venice, listen to artist ⁠Taloi Havini⁠, winner of Artes Mundi 10, on their film Habitat (2017) at Mostyn in Llandudno, and work with Ocean Space in Venice: pod.link/1533637675/episode/e30bd079e3b389a1d7e68f5e2937a797On archaeologist Marija Gimbutas, hear Emilija Škarnulytė on their film installation, Burial (2022), part of Folkestone Triennial 2025: pod.link/1533637675/episode/ZmJmZTIzMGItOTg0OC00YjhhLThkMjMtMWQ3Y2E5ZDU5MDAzAnd for more about Southampton's coastal connections to Europe, hear curators Ros Carter and Sofie Krogh Christensen on Pia Arke's Camera Obscura (1990) at John Hansard Gallery in Southampton and KW Institute for Contemporary Art in Berlin: pod.link/1533637675/episode/OWVhZjc3YWItNDRiYy00MTYyLTk0ZmItZmE5MmJlZDY1YmI1PRODUCER: Jelena Sofronijevic.Follow EMPIRE LINES on Instagram: ⁠⁠instagram.com/empirelinespodcast⁠⁠Support EMPIRE LINES on Patreon: ⁠⁠patreon.com/empirelinesEMPIRE LINES is a project within the ecosystem of ⁠Radical Ecology⁠ (2025-2026).

The new AIEWF website is live! CFPs close in 2 days and we will run our first New Engineer Orientation this weekend, get your tickets booked ASAP as they -will- sell out. Take the AI Engineering Survey and get >$2k in credits and free AIE WF tickets!One of the central tensions in the agents industry is that even while there are major decacorn agent labs like Sierra, Decagon, Notion and Cursor being built up, it is also true that it has never been easier to DIY agents, with a plethora of agent frameworks like LangGraph and Pydantic and Flue, and managed agents from Anthropic and Gemini and Amazon. There has been a wave of companies building their own background agents from Shopify to Stripe to Paradigm to Razorpay, and even Cognition's friends Ramp have built their own coding agent with other friend Modal.You'd think Cognition might feel a bit threatened, but they're not - even after all this, they were way oversubscribed for the $1B Series D they just announced:Walden Yan, coiner of context engineering and Chief Product Officer/Cofounder of Cognition, invited OpenInspect's Cole Murray to talk about why the Devin is in the Details.Full conversation live on the pod today: In retrospect, async agents were the most AGI pilled bet you could make in 2024 - the models weren't good enough yet to vibecode, and people didn't trust AI enough to let it rip, nobody (including early Cognition) was sure about the form factors. Now it is obvious:* The first wave of AI coding tools made the developer faster but remain heavily in the loop. Copilor and Cursor's tab autocomplete are prime examples However, the workflow was still heavily centered around and bottlenecked by the developer's local workflow: a developer in an IDE, watching the model, accepting or rejecting changes, and pushing code one interaction at a time.* The second wave was local agents: Claude Code, Windsurf, Cursor's agents pane: first one and increasingly many terminals all running concurrently.* The current Age of Async Agents points to a different future focused more on agent orchestration which drives end-to-end development.According to previous guest Steve Yegge, there are finer-grained 8 levels to agent adoption, but we have collapsed it into three.As Cursor's Michael Truell put it in The third era of AI software development:Cursor is no longer primarily about writing code. It is about helping developers build the factory that creates their software. This factory is made up of fleets of agents that they interact with as teammates: providing initial direction, equipping them with the tools to work independently, and reviewing their work.The agent should not sit solely inside the developer's flow. It should be setup to work in the background so that you can give it a task, a repo, a machine, a shell, a browser, tests, memory, and review loops to go do the work somewhere else.In less than a year, the sentiment has shifted from avoiding multi-agent systems:to suggesting approaches that actually work:From coining “context engineering” to building the infrastructure behind Devin's 7x PR growth and jump from 16% to 80% of commits across Cognition repos, Walden Yan has had a front-row seat to the background-agent shift. In this episode, Cognition co-founder and CPO Walden Yan joins swyx alongside Cole Murray, creator of OpenInspect, to unpack why everyone is building their own Devin, what changed after the December 2025 model inflection, and why “spec to pull request” is now becoming a real production workflow.We go deep on the architecture of background agents: harness-in-the-box vs out-of-the-box, why Devin separates the “brain” from the machine, why repo setup is still one of the hardest problems, why Docker is not always enough, and how full VMs, snapshots, scoped secrets, GitHub bots, Slack integrations, and video-based testing all fit together. Walden and Cole also dig into memory, MCP limitations, multi-agent orchestration, AI code review, SRE auto-triage, PMs shipping code from Slack, Windsurf 2.0, hybrid frontier/sub-frontier systems, and the real failure mode of uncontrolled vibe coding: your codebase regressing to your worst engineer.And as agents eat software… and software eats the world… you can draw the conclusion on what is next:We discuss:* Why the engineering world is waking up to background agents and cloud agents* The December 2025 model inflection that made spec-to-PR workflows practical* Devin's 7x merged PR growth and rise from 16% to 80% of commits* Why Cole built OpenInspect as an open-source background-agent system* The economics of $20/seat agent products and why monetization is tricky* What Cognition actually sells beyond Devin: infra, onboarding, integrations, and adoption* Harness in the box vs out of the box, and why architecture matters* Why Devin separates the brain from the machine for security and permissions* Repo setup, scoped secrets, Docker Compose, and agent-ready dev environments* Why full VMs matter when agents need to run real applications and test them* Android, macOS, Windows, nested virtualization, and machine-specific agent work* Why testing is much harder than “computer use”* Screenshots, video verification, and the “I know it works” merge moment* GitHub UX, Devin Review, AI reviewers, and agents responding to PR comments* Why MCP alone is not enough for first-class Slack and enterprise integrations* Memory, Knowledge, skills, Claude.md, and why retrieval is still unsolved* Devin's auto-generated memories and the challenge of memory pruning* Always-on agents as permanent PMs for issues, tickets, and product areas* Sub-agents, meta-Devin management, and what multi-agent systems actually add* Why pure auto-merge vibe coding breaks down after about two weeks* AI code smells, lint rules, reward hacking, and Semgrep for agent-written code* GitAI, inline context, and preserving the “why” behind code changes* Local testing, mock servers, older codebases, and preparing companies for agents* Windsurf 2.0 and the handoff between local foreground agents and cloud background agents* SRE auto-triage, support workflows, and agents as first responders* PMs, marketing, and non-engineers creating pull requests from Slack* AI agent budgets, $1k-$5k per engineer spend, and hybrid frontier/sub-frontier systems* The rise of autonomous coding factories and who Cognition is hiringWalden Yan* X: https://x.com/walden_yan* LinkedIn: https://www.linkedin.com/in/waldenyan/Cole Murray* X: https://x.com/_colemurray* LinkedIn: https://www.linkedin.com/in/colemurray/* OpenInspect / Background Agents: https://github.com/ColeMurray/background-agentsTimestamps00:00:00 Introduction00:00:43 Why Everyone Is Building Their Own Devin00:01:57 Devin's 2025 Ramp: 7x PR Growth and 80% of Commits00:03:49 OpenInspect and the Rise of Open-Source Background Agents00:07:59 What Cognition Actually Sells Beyond Devin00:09:56 Background Agent Architecture: Harness In vs Out of the Box00:12:08 Separating the Brain from the Machine00:14:07 Repo Setup, Secrets, Docker, and Full VMs00:19:13 Why Testing Is Harder Than Computer Use00:22:40 Video Verification and the “I Know It Works” Merge Moment00:23:19 GitHub UX, Devin Review, and AI Code Review00:25:42 MCP, Slack, and Enterprise Agent Integrations00:28:59 Memory, Knowledge, and Always-On Agents00:36:16 Sub-Agents, Multi-Agent Orchestration, and Meta-Devin00:43:55 Vibe Coding, Auto-Merge, and Codebase Decay00:48:38 Agent Infra, VPCs, Cloud Providers, and Fast VM Restore00:52:25 AI Code Smells, Reward Hacking, and Code Review Systems00:56:10 Making Codebases Agent-Ready00:58:30 Windsurf 2.0 and the Local-to-Cloud Agent Handoff01:01:15 SRE Auto-Triage, PMs Shipping Code, and Agent Use Cases01:04:32 Agent Budgets, Hybrid Models, and Autonomous Coding Factories01:06:51 Hiring at Cognition and OpenInspect Consulting01:07:45 OutroTranscriptIntroduction: Walden Yan, Cole Murray, and Context EngineeringSwyx [00:00:00]: All right, we're in the studio with Walden Yan, co-founder of Cognition, CPO.Walden [00:00:08]: Happy to be here.Swyx [00:00:09]: Which is a cool title. And coiner of context engineering.Walden [00:00:15]: Although I think there are many people who'd used the terms in various ways beforehand, but I did find that people, both internally and externally, enjoyed the upgrade from prompt engineering or model wrapping into maybe a more thoughtful way to build agents.Swyx [00:00:33]: For those who haven't caught up on that, I have on screen the Don't Build Multi-Agents post, which you should go read on and we might refer to, and Cole Murray, who created OpenInspect.Cole [00:00:43]: Great to be here.Swyx [00:00:43]: So let's talk about it. Everyone is building their own Devins. What's going on?The December Shift: From Handholding Models to Autonomous PRsCole [00:00:51]: So I think the engineering world is waking up to this idea of background agents, cloud agents, whatever you'd like to call it. And I think we saw a shift around the December timeframe of 2025, where the models Opus 4.5 and GPT 5.2, they reached a capability where we moved away from handholding the model and being able to actually more or less autonomously drive the model. And what I mean by that is that we could pretty much go from a specification to a completed pull request, assuming the spec was good enough, with very little friction. And that paradigm alone, I think, changed a lot of how we interact with agents, and opened this world where background agents became more practical.Swyx [00:01:41]: I think for Cole, everyone experienced this in December, but I feel like there was just this increasing ramp, right? There was this moment which was, I think, Sonnet 3.7, where, You guys rewrote Devin in one night or something. So describe 2025 or how it felt from your side.Walden [00:02:01]: In retrospect, we always thought it was ramping up, but then even now, over the last three, four months from today, it's been ramping up even faster. So it's almost funny to be talking about how, big of a leap Sonnet 3.7 was, and honestly, a lot of it was stripping out parts of Devin that were no longer needed with that jump in of intelligence. But I also just think that a lot of the recent leaps, especially, you look at, models like Opus and the latest GPT models, they are reaching levels of autonomy where people are actually finding that they actually can just be hands-off. And people who were once debating, “Oh, do I need to be in the weeds with my model in the IDE? Can I just completely move it off into the cloud?” That's a more serious conversation, and we've seen that in all of our growth charts. Internally there's this funny graph where our usage has, of PRs, our merged PRs, has grown 7X since I forget what it was called.Swyx [00:02:57]: I think Dev, maybe tweeted that. Yes.Walden [00:03:01]: it grew like 7X over, the last, I think it was, two months, three months, something like that. And then you see our engineering headcount growth. It's, gone up by, 10% or something.Swyx [00:03:11]: We were, we were afraid To release this. So this is Devin commit percentages on all Devin repos, was 16% in January and now 80% in March.Walden [00:03:25]: It's a big shift right now. And so it makes sense that a lot of people are now thinking about, buying Devin, but also maybe, trying to build their own and there's Lots of I have a lot of fun building Devin, so I can see why other people would want to build their own cloud agents as well. Matt, well, maybe it's good to hear, what initially inspired you to try to build OpenInspect?OpenInspect: Ramp, Cloud Agents, and Open SourceCole [00:03:49]: OpenInspect came about, through primarily my clients observing how they were using tools like Claude, OpenAI's Codex at the time, and seeing some of the friction that they were having with it. Primarily the Claude was being used through Slack, and a big issue they ran into was that the sessions that were launched were specific to whoever called it via Slack. And so if a PM was the one who invoked the session and they would then go to pass context to engineering can't see the session. And that in itself was a deal breaker because the PM, “Hey, engineering, can you jump in?” But there's nothing to jump in on unless they're copy-pasting out or the single response that came back. And so seeing some of these problems, I had built a similar architecture internally, just to experiment with, test out different ideas as this trend of moving off of localhost was starting to become, And as Ramp released their blog post, I had a lot of the pieces for this already in place, and just thought it would be funny to, see what Claude could do just purely from the blog post. And on my X account, there's actually a thread of where I live tweeted, going through thisCole [00:05:14]: comparing GPT and Claude as both of them are going through it.Swyx [00:05:17]: On the announcement thing or something else?Cole [00:05:19]: right after it got released. We can put it in the show notes. Yeah, it was helpful that I had already knew how to verify the system. I knew what I was looking for. I think Ramp did a great job of really illustrating, the technical aspects of how to build something. It was much more than just like, “Hey, we built a great system.” It was, “And here's how you can build it too.” And so, I resonated a lot with that, just with the problems that I was already seeing, and I thought that, looking around, I didn't really see anything in the open source community that, met this type of system. I think there's a lot that run, in localhost like Superset, Conductor, and many others.But nothing that was actually running in the cloud. And so, I built it, and I thought it was interesting to just open source it and allow anyone to then have a foundation that they can mix and match on top of.The Business of Background Agents: Open Source vs. DevinSwyx [00:06:16]: So literally after Devin was launched was, there was OpenDevin Which became All Hands. I don't know if you tried that orWalden [00:06:22]: I was going to say, one of the things that interested me a lot with OpenInspect was, you didn't try to go make it then something you monetize. There are a lot of, I think, these open source projects would then go and really try to, raise VSwyx [00:06:36]: That's why no OpenDevin. Yeah.Walden [00:06:38]: yeah, and how did you think about that? I thought that was very interesting.Cole [00:06:44]: I thought, and just what I had seen across my clients, was that having a background agent system is going to become a critical infrastructure within their company. And so because of that, I think that I wanted to open source it so that they could fork it and put in whatever customization they wanted. To that question though, I get asked all, “Oh, are you going to raise? Are you going to turn this into a service?”Walden [00:07:08]: I'm sure you've gotten offers.Cole [00:07:09]: but primarily I don't want to do that for a few reasons. One, I think that I don't want to compete for, $20 a seat. I think that is just a really difficult business. I think it's very easy to copy the main pieces of it. Again, I built this fairly quickly. And I think because you are not owning, I guess, the entire stack, it's hard to monetize. You have money being made at the sandbox layer with Daytona, E2b, many other players. You have money being made at the model layer. And you sit in this weird in-between gray area where what are you actually selling? You're selling, I guess, the infrastructure. You're selling, the integrations maybe.Swyx [00:07:55]: let's ask the guy. What are you What are you selling?Walden [00:07:59]: Well, yeah, there's multiple layers to this in practice, and actually it's funny you mentioned the infrastructure, ‘cause when we got started building Devin as well, we had to go figure out how to make the infrastructure as well because,Swyx [00:08:10]: You had to build this two years before everyone else,?Swyx [00:08:15]: Including, the model sideWalden [00:08:17]: It was not, it was not very polished at the start, when we just built it off of raw VMs from cloud providers like EC2, the boot up time was so slow, I think, And especially then, turning off the machines, saving them, and then to be able to bring them back up again when the, when you want Devin to wake up again later. It would just be out cold for like 10 minutes because that's just how long these systems took. They were not built for this repeated down and up usage. And so we actually had to go do all of that. And as a result now, one thing we offer when we go and sell Devin to people is, you don't have to worry about all the compute side of things. We'll make it work. We'll make it work in your cloud if you want it to. But aside from the product, and I want to go into the agents and the tuning of the intelligence part later, but I think a big part of what we do at Cognition as well is to just make sure that your company learns and uses and adopts these coding agents. ‘Cause I think for especially the largest enterprises in the world, you find that there is a lot of people who want to move over to using AI for their day-to-day workloads. But because of the way projects are planned, because, not everyone is literate in using AI in these ways, having a team of engineers who can actually go in and onboard you, set up all the integrations you need, the automations you need to really get to that level of, leverage with AI, is super helpful. And so We do that. We show thought partners to the customers that we work with as well.Swyx [00:09:56]: So let's talk about, architectural stuff. I think that's always, that is something that was the topic of conversation between the two of you. Is this, the mental model that you want to start with or something else? I'll just leave the floor open to you guys.Agent Architecture: Harness in the Box vs. Out of the BoxCole [00:10:11]: I think, maybe we can start here as just a general what are the pieces of a background agent system. And then maybe we can go into some of the nuances of, Decisions that you can make.Swyx [00:10:22]: But I guess I also Like, what, maybe what Walden is saying is the agent is like in this open code box, I guess. Right? This is infra, and then there's, that's the agent. And you had this discussion about whether you put the agent in here or in Out externally. Can you tease that out?Cole [00:10:39]: In a background agent systems, you have a decision to make of where the agent is actually going to run. This is typically described as the harness in the box or out of the box. With running the agent in the box, you're making some trade-offs by doing that. The negative trade-off you're making is primarily security. Because the agent is running in that box, unless you otherwise design it, all of your secrets need to go into that box as well. And given the nature of AI, it can be unpredictable, and you could very easily end up accidentally exfilling your secrets, or other unintended behavior. Now, the out of the box is the idea that we are going to have the actual agent running not directly in the sandbox, and we will have, quote-unquote, the brain of the agent running in some type of worker, control plane. That sandbox then is going to serve as the hands where the brain is basically operating and making tool calls into that environment to manipulate it. I guess other trade-off that you're making between the two systems is that, in my opinion, running it out of the box is much more complex because, you have state that has to be managed, whereas if you're running it in the box, all of the state of that agent is actually in the box, and yes, it's you could persist it elsewhere, but it's all localized and you have less concerns to worry about.Walden [00:12:08]: I think a lot of that, what you mentioned, is why we actually from the start built Devin to what we called separate the brain from the machine. The other thing that this allows you to do is reuse any existing infrastructure you have for dev boxes Perhaps. And so you don't have to worry as much about making a new type of dev box that has all the dependencies the brain needs, as you mentioned, the secrets the brain needs as well. One thing that we've seen some customers run into is, you have a GitHub app and you want Devin, your agent, whatever, be able to interact with GitHub through this application, but then you have different users with different actual permissions. If they are all interacting through the same GitHub app and there's no actual, separation between the system that decides, what it does and the actual secrets on the machine, then you run into an issue where, okay, it's hard to do the separation. But in practice, with Devin, it's much easier because we just say whatever you put on the machine, that is, the scope of basically what the user is free to do, what the agent is free to do. So only put the most scoped secrets on that machine, and then the brain is fully not accessible from the machine. So you don't have to worry about messing with the, any of the most secure parts of the brain if the user is free to do whatever they want with the machine.Swyx [00:13:31]: I was going to just bring, I have this, chart from OpenAI, where I don't know if this is, in the box, out of the box. That is something that they do use to describe it. And then also recently Anthropic did, managed agentsSwyx [00:13:44]: Which is, this is their thing. I don't know. It's all, it's all variations of the same pattern, right?Cole [00:13:49]: So this would be out of the box.Swyx [00:13:51]: Which, is preferable for them because it's less work?Cole [00:13:56]: I would say it's more work.Swyx [00:13:58]: It's more work?Cole [00:13:58]: But it, in my opinion, it is the better architecture of the two. It's just, you're taking on a bit of complexity by doing that.Repo Setup, Docker, and VM-Based Development EnvironmentsWalden [00:14:07]: One thing I've not seen a lot of other players do well is how do you manage what's actually on the box? And this can be complex for many reasons. Let's say you have a big repository that's changing and updating a lot with changing dependencies. How do you make sure that the working environment of the agent actually stays up to date, has all the credentials it needs to, let's say, run the app and test it, and all the things you want your autonomousSwyx [00:14:34]: So a repo setup.Walden [00:14:35]: Exactly. So in, internally At Cognition, we call this repo setup.Cole [00:14:39]: The hardest part ofWalden [00:14:40]: It's been a perennial problem since the start of the company, of how do we help people get this set up? Because not everyone just has, working cloud environments working out of the box. And do you find this to be a common problem withSwyx [00:14:53]: How do you solve it?Walden [00:14:53]: Your clients?Cole [00:14:54]: This is a very common problem, and through my consulting, this is a lot of what I help teams do. A lot of teams don't really have great developer environment setups, if any. A lot of the times it's, “Go talk to Bob and get the secrets,” and that obviously doesn't work when the agent needs to actually set this up. And so a lot of that, most teams are using Docker Compose or some type of microservices. And so for theSwyx [00:15:19]: Even in prod?Cole [00:15:20]: Not in prod. With the OpenInspect, you are using this primarily to interact, and make code changes. There is other use cases, but you can hook, whether through CLI, MCPs, other tools, you can then hook that into your production systems primarily for, SRE type use cases. But you are not, necessarily, trying to test your prod internal microservice through the system.Walden [00:15:48]: And you mentioned Docker Compose. I think one direction we saw some of our friends take early on was, using Docker containers as the level of abstraction for their models. There's lots of reasons, I think, why Docker containers are not great. One thing is, Docker container's not really a true security boundary, for one. But the other is, if you are running real applications, a lot of times those applications use Docker, and then you have to think about Docker in Docker, which is, really weird. And so I think part of, the really hard challenge of getting VMs to work, why did we do that? Well, it was because we realized that you actually needed, full VMs to be able to do these types of things. And especially nowadays where there's actually value in running the application and clicking around and sending you screen recordings of these things. The value just, keeps adding on top of that. But it is a decision I see people run into when they try to build their own systems, is, “Oh, do we, in addition to this, do we put the agent in the machine or out of the machine? Do we use Docker? Do we use something else?” What do you recommend people nowadays?Cole [00:16:57]: I think Docker is a good solution for maybe not running the agent, but running your infrastructure, because that is more or less the same setup your engineers are probably already using. If they're not, then I don't know what they're using. But they're probably already using Docker Compose.Swyx [00:17:14]: I've always had a small candle for web containers. I don't know if you guys have tried them before.Swyx [00:17:19]: To me, they were, supposed to be like Docker Light.Cole [00:17:22]: Is it?Swyx [00:17:22]: I don't know.Cole [00:17:22]: No, I haven't tried it. But yeah, I think any environment that you've set up that is a good experience for your developer naturally lends itself to being easy to set up for the agent. And once you figure out that local developer story, you've more or less solved the agent in a sandbox, environment setup. OpenInspect does have hooks as well, where you can, run a setup SH script that will pre-install everything. You can then pre-snapshot that build so it starts instantly, and then there is a second hook to actually then, restore the state of the sandbox when it comes back. And so you can already have all of those microservices running and basically get the same experience that you would on your machine within the sandbox.Testing Agents: Computer Use, Screenshots, and Real App WorkflowsWalden [00:18:08]: Another thing that we've been thinking a lot about is like Different VM service offerings. Have you had customers where they needed like macOS specific VMs or like Windows specificWalden [00:18:20]: VMs?Walden [00:18:22]: There are like many technologies in the world that only work on specific types of machines, right? If you're building a.NET application that has to run on Windows or like, maybe more commonly if you want to build iOS or macOS Does that workSwyx [00:18:32]: Does Commission supportSwyx [00:18:33]: Choices like that?Walden [00:18:35]: The fundamental architecture we do, because we do the separation, it does support, but the actual work in progress is happening right now on these. Another thing that we've actually recently added support now for, it's in beta, is doing Android development. To do that, we needed to support, I think, nested virtualization within our machines because the VM itself is like a, is a virtualized Firecracker instance, and then you had to then run another Android emulator inside. And there's like weird performance issues that like, it, which is why it's like still in beta. We have to think through these problems, but it unlocks a lot for anyone who wants to do Android development.Swyx [00:19:13]: I was trying to find like a reference video for the testing thing. I couldn't find it, but I think you worked on the testing, capability. Why call it testing and not like computer use or I don't know, it's, what's the general Category of problem?Walden [00:19:26]: I think that when people think about the ability of an AI to run your app and test it, I think they actually over-index on the computer use part of it because computer use in my mind is the literal, okay, you want what button you want to click. Can you emit the right coordinates to go click that button? I think testing is actually a really interesting likeWalden [00:19:48]: Problem-solving, challenge for these AIs because if you wanted to do arbitrary testing, imagine you make a change that spans the frontend and the backend, maybe, even some other like even more deeply nested service. To actually test that change, we have to reason through what-- how do you first run these applications to orchestrate with each other with the right version of the code? Then, okay, how do I trigger the feature or how do I make the thing actually happen? And this can get arbitrarily hard, maybe you have to be an admin. Maybe a certain thing has to be feature flagged on. Maybe, you have to like run two sessions and then send us a very specific word into one of them to trigger a specific behavior. And figuring out how do you do that requires a lot of code base context, requires, a lot of orchestration that we've specifically done. And in some cases, we found that you actually, no one frontier model can actually do this full end-to-end task itself.Walden [00:20:42]: We've seen cases where we actually had to orchestrate different frontier models together to solve this problem together. That is where we spend most of our time when we think about this testing problem, not so much the computer use part. Computer use for what it's worth has gotten a lot better with recent models and it's made that part of the job certainly easier.Swyx [00:20:58]: Especially with like even 4.7, that they released yesterday, apparently like way better in terms of the vision stuff, which is going to be encompassing computer use.Walden [00:21:08]: Having evals for all these as well is something that like takes a while to build up. And having the evals be right is tricky as well. Do you ever see like, clients who are building their own agents have to start standing up evals to make sure things don't regress?Swyx [00:21:25]: Not so much evals in the traditional sense, but specific to the testing part that has just gone in. I just added support for screenshots And in theory you can also do video. I need to put in a plugin to do that. But they do show up natively, and it was a very heavily requested feature, especially after Cursor's recording came out. I think that was very enlightening for everyone of like, “Oh, this is a very good feature to actually have.”, I think with Devin you guys have had this for a while.Swyx [00:21:57]: Oh, yeah. See how screenshots work. Yeah, I don't know if there's anything, super and not obvious. It's like once what feature to build, you can just prompt it and it Will mostly work.Walden [00:22:09]: I think to Walden's point, though, the computer use is a subset of the larger testing problem, and I think that's very specific to the code base that you're working and it's not something that, out of the box that you could just solve it. The-- you do need the code base context to actually know how to test it. And I think in the case of a background agent system, you fortunately do have that code base locally that what is changing and could then inspect it and use that to drive the model.Swyx [00:22:40]: For those who haven't seen it before, this is an example of how it works. You, after the PR is done, you click testing approved, and then it sends you back a video. What I really like is that it labels, It's very small here, but it actually labels what it's testing. And then it-- and then you actually see the cursor and everything. So I don't know, yeah, the engineering in this, just Whatever you want to show. ‘cause this is like, this is one of those like, oh, few of the AGI moments, right? ‘cause Once I look at this, I actually don't I wish I can just merge inside Of Slack instead of going to GitHub ‘cause I don't need to see the code. I know it works.Walden [00:23:19]: Maybe a new feature in Cursor. Yeah, the annotations at the bottom was also a big difference for me when I, when I added those.Swyx [00:23:27]: It's just like, what am I looking at? What are you trying to demonstrate?Walden [00:23:30]: Exactly. There's a surprisingly long tail of small details that ends up making a big difference for this end metric of like how fast do you actually merge the code in. One experience that we spent a lot of time tuning early on was what is the right experience on GitHub for these tools. Because I think, most tools out there when you build the agent, you'll think about, oh, it'll create the PR for you. We try to take that a step further and say, “Oh, what if we actually made sure you could interact Devin, with direct Devin directly on GitHub?” And so we made sure that you can comment on GitHub, and Devin would actually receive those comments and address them back. But there's actually quite a bit of tuning you have to do here because you can imagine that actually like-We recently have Devin Review, for example. Devin Review will post comments on his own PR And then Devin has to then goGitHub Workflows: Devin Review, Comments, and PR AutomationSwyx [00:24:23]: He answers his own comments, which is Really loopy. So like, yeah, I like that it just updates here that it's, that I have commented But usually it's just me saying like, “Hey, merged, fix any merge conflicts.”Walden [00:24:37]: The, so when Devin fixes his own comments, you might be scared that, oh, maybe I'll infinite loop. But we've put a lot of work into making sure it doesn't, both by making sure that the comments are high signal, but also that the agent is thoughtful about what comments it immediately goes and tries to fix, and what comments it's like, “Wait a second, I think you're wrong.” Actually, that's one of my favorite moments is when Devin tells me that I'm wrong, when I try to get it to do something different. But tuning that behavior, actually makes a big difference in terms of how useful the actual GitHub experience is.Cole [00:25:06]: I think to touch on that as well, I think having the AI reviewer integrated into the system is a critical part of this background system. OpenInspect does have that. It has a GitHub code reviewer that you can control the prompt. It does do comments as well. It doesn't do them automatically yet. The capability is there, but it's not fully used.Swyx [00:25:27]: So you have to ask for it?Cole [00:25:28]: you do, yeah. You can tag it on GitHub, and then whatever you named your, GitHub bot, it will then follow up on it. It will then, if you have merge conflicts or whatever you have asked it to resolve, it will then resolve it, but it doesn't do it automatically yet.Integrations: Slack, MCP, and First-Party Agent InterfacesWalden [00:25:42]: Well, I'm curious, what is, the most common thing that people end up requesting, that they still need on top of OpenInspect when you help them go implement it?Cole [00:25:52]: I think a lot of it comes down to actually integrating it into the company. It's one thing to have the background agent system set up, but if it isn't actually integrated into your larger ecosystem, it isn't that useful. It is useful to be able to kick off sessions, but what we really want to be able to do is hook it into all of our other systems, whether that is the production database with read-only credentials, the logs, a Confluence or internal knowledge-based system. I think that is where I see the huge leap for companies, and that can be a challenge for companies as well who are maybe not familiar with exactly how to approach it, especially if they're in environments that have more compliance type things where, access control can be pretty big and how do you deliberately think about these problems, I find to be, one of the problems that comes with a system like this.Walden [00:26:46]: The thing we found is So, MCPs, obviously it has been like this, really big explosion of, oh, you can go, integrate it with all these different things. But to actually get the integration right and the and get the right experience, oftentimes we found that we had to go build our own ad hoc things. I think Slack is a great example of this. You could give your agent a Slack MCP and okay, it can post messages back to you on Slack. But we actually use Devin like a coworker in Slack, and that's how it's been built from the ground up. But to do that, you actually need to, support webhooks that come back, right? And then Devin has to respond in a natural way and then hopefully don't spam your threads too much and annoy the people in your company. So you got to tune that experience just right. Especially when there's a lot of back and forths, we find that we actually have to go beyond the simple MCP integrations in these places.Swyx [00:27:39]: I just pulled up the MCP marketplace. I know this is a Fair amount of work. Is the answer to eventually take first party control of all the top MCPs? Is that theWalden [00:27:48]: I would love a world where you could have something that's more expressive than MCP. That, goes both ways, not just a set of tools, but a proper system that interacts back and lets it Have the right experience with all these interfaces.Swyx [00:28:03]: So there actually is sampling in the MCP spec, but nobody Uses it, right?Walden [00:28:07]: And so I think that's the other part is, actually we found that when the MCP spec starts to get too complicated, it starts to lose its original promise of Being like a simple one-step connect. Now then we have to go figure out how to support all these different variations of things and It starts to look a lot like just building the first party integrations in a lot of these cases now.Cole [00:28:29]: I think it matters, too, how critical it is to your company, right? If this is something that nearly every session is going through, it probably makes sense to own it so that you can make optimizations on top of it Versus just whatever is off the shelf.Swyx [00:28:43]: Awesome. Other than MCPs, what else, sorry, well, I don't know if that's Narrowing in too much on, integrations. But what else? What other elements of building OpenInspect or Devin that you guys really sink on?Memory and Knowledge: What Agents Should RememberCole [00:28:59]: I think, a problem that comes up very frequently is this idea of memories or knowledge base.Swyx [00:29:05]: Oh, boy. How do you solve it?Cole [00:29:08]: so not solved yet, is the short answer.Cole [00:29:11]: it's something, there's a open issue for it, someone asking about it.Swyx [00:29:16]: There's, I, D Wiki hasn't indexed anything about memory yet.Cole [00:29:20]: how I'm seeing it solved across my clients is primarily through skills. I find that skills can be a good gap within that or updating Claude MD, but I think memory as a whole is a pretty unsolved problem, and it is why I've been hesitant to add it. I think there is parts of memory and that can be addressed, but I think as a whole it's a very difficult retrieval problem.Swyx [00:29:44]: Oh my God. RAMP didn't write anything about memory? I see zero search results.Walden [00:29:50]: No. Memory can be quite tricky to get right because it's the retrieval, but also the generation of the memories that can be really tricky. You don't want it to just like Remember very specific details.Swyx [00:29:59]: Walk us through the Devin memory journey because I know there's been a journey.Walden [00:30:03]: the first version of memory that like stuck around for a while was A system we have called Knowledge. And the idea was we wanted it to pick up things over time and not need the user to be proactive about teaching Devin things. So, okay, any time you remind Devin, “Wait, no, that's not quite the way you're supposed to use Git”Like, we actually want Devin to say, “Hey, do you want me to actually just remember this for the future?” And for you to just basically quickly approve or reject and for it to build up over time. ‘Cause I find that, 95%, I think, or some crazy stat like that of the memories that Devin has are all through these auto-generated things. Very few people actually just want to sit down and write big docs on Here's how you're supposed to work with the technology, et cetera. The generation and the retrieval has been something that we've been trying to tune a lot over the years. Generation, you don't want it to remember something like, if you asked one time to like, “Oh, please open as a draft PR,” you don't want to be like, “Oh, everyone forever now should get their PRs as draft PRs.” But you do want some, conveyor. Maybe you want to say like, “Oh, Cole generally likes, things to be created as draft PRs.” Same with retrieval, if you have thousands of these memories, how do you actually make sure they're retrieved at the right time? And that can be quite tricky to do right without exploding the context with a bunch of useful yeah, useless information. Surprising amount of just, eval work to just make sure that, memory is, remains a reliable system as new models come and go.Cole [00:31:31]: Do you have anything that you could share on, memory pruning? And like the temporal aspect of memory?Swyx [00:31:36]: Deleting and forgetting?Walden [00:31:39]: The, today, the, So the things they could do is it could edit memories. And so if your memory used to say like, “Oh, Cole likes to open everything as like a draft PR,” then you can imagine, “No, don't do that.” And then it'll say, “Oh, do you want me to update the memory to be Cole now want everything as, open PRs?” I think that at the same time we don't know if this is going to be the final version of the system. Whatever we have here will probably, translate into the new system that we'll be coming up with. But I think one big difference between two years ago and today is these agents are really good at using anything that resembles a file system natively. And so part of us are, is thinking, “Oh, should we rebuild memories to feel more like a file system that we let the agent navigate on its own?” That's been an interesting exploration. Also similar ideas in the scale space.Swyx [00:32:35]: I am pulling up OpenClaude's memory thing right now. So memory, OpenClaude has like this like daily memory journal thing, right? And you can I mean, that is a file system you can grep through and is a source of truth. I don't know if it's the best. It's probably super noisy, but at least, if you lose something you can discover it or you can apply some, forgetting algorithm to, more ancient memories that don't get recalled again or something. I don't know.Walden [00:33:01]: One thing we've been trying to do to push the boundaries of how you use agents at your company is letting an agent basically have a very similar file, a memory.md or something, and just like be your permanent PM for a specific set of issues maybe. So we have like some Slack channels internally, maybe a Slack channel dedicated to, a specific product like DeepWiki maybe. And you can imagine that, or you want a Devin that never stops, it's just always awake, but it has this like memory dock that it can just maintain for itself about, okay, what are like the number one priorities of what we have to fix and prioritize? Who is responsible for some upcoming work? Maybe they'll even Devin will even tag you on some recurring basis. And so it's been an interesting move to see, okay, how can we actually use Devin for more than just engineering? Can we actually upstream above the engineering process and maybe it's just Devin creating tickets, which then maybe some humans do, but then maybe other Devins do.Swyx [00:34:00]: One of my more fun automations is go research competitors and just suggest stuff to me on a weekly basis. That's the automation. I can't find it right now, but basically it just like, “Look at competitors and suggest things.” “And here are three things that you've suggested that I don't want any more of,” and you just stick that in the prompts. But like I wish actually So for like when I, for example, when I reject a PR, I wish that it updated memory so that I can then just not have to go up, go back and update the scheduled, sync, but anyway, feature request.Walden [00:34:31]: what? We might change it soon. I guess OpenInspect, in the time you've been around, has there been anything you tried to implement but then you had to like undo and like do a different way?OpenInspect Architecture: Webhooks, Control Planes, and Agent StateCole [00:34:41]: Nothing yet, but something that is on my mind. The initial way that I built it was that each of the integrations lives as its own package. And so you have The Slack bot, which is what's handling the webhooks, and then is basically interacting with the control plane. As I'm seeing the system starting to be more integrated, specifically with the GitHub bot integration, I'm considering bringing that all into the central control plane because especially now I want to start, And a request that I'm getting is the ability to monitor, the actual, pull requests being merged, as well as just tracking ofSwyx [00:35:19]: What do I have open?Cole [00:35:21]: What do I have open? How many of these are getting merged? How many comments are showing up? To just understand the health of the system. And so in the case of a GitHub app, you only have one webhook. And so then it's a question of do I put that webhook in that GitHub bot package? That's weird. It doesn't really make sense to live there because that package is more for like the code reviewer. Or do I like centralize it? So that's something that's on my mind of, making that decision. I think the other one we touched on earlier is the harness in the box versus out of the box. I think long term the architecture will eventually come back out of the box. Some of the newer tools that I've added are calling back into the control plane so that you don't have the secrets in the sandbox. And so I think long term I probably will pull the actual, agent out of the box, but I think for now it's fine.Subagents and Multi-Agent Systems: When Parallelism Helps or HurtsSwyx [00:36:16]: Just, a quick question on pulling the agent out of the box. I'm One thing I'm very bullish on this year is agents calling other agents or spawning sub-agents or Whatever you want to call it. Does that make it harder or easier? I can't tell. Because if the harness is in the box, you can just spin up more boxes. If the harness is outside the box, then you're, it's less easy because you are, you have a unicorn pet of a, of a harness that's, living outside the box.Cole [00:36:45]: In theory it would be the same way, right? Whether, one agent has launched many, sub-sessions within it, OpenInspect, for example, can launch sub-sessions and actually create other environments and then monitor them. In the case where it is out of the box, that would basically just be an additional session that's running. And so that session is also running outside of the box. It's running in your worker plane, wherever you're running this. And then you really just have to think about how does your top level agent then interact with it. I do think it can be more complex, just ‘cause again, you have now a more difficult architecture. But I think if you figured it out once, it's probably fine.Swyx [00:37:26]: Well, then I'm just, throwing it open to you in terms of, I call this like meta Devin management. Which is like the, Devin's calling Devins or Devin scheduling Devins or querying trajectories or anything like that. What have you built or unshipped, anything?Cole [00:37:46]: I think one of the surprising things we've seen is that a lot of the ways that, these, separate agents work with each other, and you want them to, parallelize their work, has still mostly followed the same manager sub-agents regime. And a lot of people I think are excited about this world where you have swarms of agents that, talk with each other all over the place. We've actually given Devin an MCP so they can just go arbitrarily message other Devins And create new Devins, et cetera. But I guess, it somehow creates, a really chaotic world in that sense. And so we've still found that most practical use on a day-to-day basis has been one single Devin.Cole [00:38:33]: Figuring out how to segregate the work and get, have other Devins work on it in, a relatively isolated sense, each with their own boxes Not sharing machines, so there's, a very little room for conflict is the regime that you have to create today.Swyx [00:38:50]: I'll call out, the experiments from Cursor, right? This is Wilson Lin's work on Single agent to multi-agent, and you're obviously famously on the side of don't build multi-agent. But they went through the whole thing, only to arrive at, this Which is exactly what Devin has, I think.Cole [00:39:08]: I think there will be a revision to that post at some point AboutSwyx [00:39:12]: Tell us about itCole [00:39:12]: I think multi-agents were very much not at all possible a year ago. You do see more multi-agent experiments today, but you can argue, are they really multi-agents, or are they just just, tool calls,? There are people who, will create sub-agents to go look for XYZ file, XYZ implementation. Has really nice context management benefits because all of the tool calls and tokens that it spends then get collapsed back to just the answer for the main agent. There's a lot of benefits to doing this. We basically have Devin do this with Deep Bookie, make a call out to Deep Bookie, give you back the results, but that feels like a tool call,? It's not like these, two collaborators actually talking back with each, back and forth with each other. But I think the thing that gives me the most bullishness that multi-agents might actually be possible is actually what I said earlier about Devin will actually sometimes tell me I'm wrong and push back, and I think that demonstrates a level of maturity and communication today that makes a multi-agent world possible. One, can two agents who have seen different information come back to each other and actually figure out who is right, what is the correct implementation? They're not just, yes men. Claude, I guess is like, used to just say, what is it? “You're right,” or,Swyx [00:40:25]: “You're absolutely right.”Cole [00:40:26]: “You're absolutely right.” Yeah.Swyx [00:40:28]: The Have you seen, did you seeCole [00:40:29]: The age is overSwyx [00:40:30]: The Codex app troll in Topic? This is the Codex app. Inside of Settings, there's a little, there's a little Easter egg, right? So if you go to, the Themes or Appearance, right? There's all these, color codes, and the top is absolutely, and it's the Topic's colors. Which is such a troll. Anyway.Model Behavior: Pushback, Adversarial Prompts, and Agent SkepticismCole [00:40:53]: I love that Easter egg. Did you discover that yourself?Swyx [00:40:54]: No, it was, someone was, tweeting about it And I was like, I was like, “Is this true?” Because, sometimes people just tweet stuff to, get a rise out of you. But yeah, there you go, in Topic colors.Cole [00:41:06]: Yeah. So yeah, we're out of this regime where, it just says you're absolutely right, and they can have real conversations and real back and forths.Swyx [00:41:13]: You can prompt it as well to be more adversarial or whatever. Yeah. Okay. Yeah, that, I mean, to me, that is more intelligence, right? That is not just something that's, a dumb tool, it's actually pushing back on you I think. Yeah.Cole [00:41:24]: when you mentioned, of course, the blog posts. There was one blog they had where they fed a swarm of agents together and built a browser.Swyx [00:41:34]: That was I think that was the one.Cole [00:41:36]: You can have, likeSwyx [00:41:37]: I think it's the same oneCole [00:41:37]: Creation of it. We found a surprising success of, don't do a swarm or anything, just have one Devin, it does its own context management. Just let it keep running for a while and give it some crazy tasks. I think we asked it to, rebuild, a Windows OS system. And it managed to do it just like, going on for long enough. It'sSwyx [00:41:55]: Was this Andrew's thing?Cole [00:41:58]: there were lots of demos that we ended up not posting, ‘cause at some point we'd just be posting way too much a bunch of, Demos. But I love that because it shows that I think the multi-agent thing still has, a bit of exciting sexiness to it, which is maybe still beyond still, the actual delta it adds to the capabilities of these systems. But it's absolutely the future. I think we're heading in that direction and we can see the progress being made there already.Swyx [00:42:25]: If I were to, make one super minor pushback because I don't feel that confident about it yetCole [00:42:33]: Go for itSwyx [00:42:33]: But I've had Ryan Lopopolo from OpenAI on the pod And he's a super slop cannon, right? Oh my God, that's my coding agent being done. I downloaded this, Peon Ping. I don't know if you guys have heard this. It takes like-, sound packs from popular games like, Command and Conquer and Warcraft, and then it plays it whenever it's done. And so it's like, “Work,” or whatever, “At your command,” or something. Anyway, what I got from the Cursor code base and from Ryan's thing was that there's a slop cannon approach where you try to loosen the single agent's, bottleneck, and I feel like that is, probably an, a very important thing to try to figure out. I don't think anyone's, really solved it. Because then you just have more reviewer slop on top of the agent slop To try to wrangle it all. Ryan will probably very strongly object that I say that he hasn't solved it, but he thinks he's He thinks he's completely solved it. But I think it's still I think it's, very important, ‘cause, that is a bottleneck, right? I feel Devin is slow sometimes Because I'm like, well, yeah, this is very readable and very sensible, but also it is slower than it could be if I just, I want a button to just say, “Just ramp this up 1,000 next parallel, in parallel and just, see what happens,”? And I don't know if that's, feasible at some point in the future.Code Review, Entropy, and AI SlopWalden [00:43:55]: I And we've also run experiments internally where we've basically tried to build entire products, true products that we knew we would eventually ship, but for now, let's try to see if we can do it just by purely, vibe coding on top of each other, auto merge, no code review at all. And then there's this benchmark of how many weeks can you go onto this for Before you say, “We have the trashiest code base.”Walden [00:44:18]: “Let's actually rewrite it from scratch.”Swyx [00:44:19]: Start a new factory, yeah. What'd you find?Walden [00:44:21]: I think we found that the state-of-the-art in December was you can probably, run this for about two weeks. By the end of those two weeks, you'd find that, hey, you want to, change the color of a button. Well, it turns out this button is implemented in, 10 different places, and they, have All these different variations, and oh, you forgot one of them, and actually it's a slightly different color in one spot. And you're like, “Okay, this is too much to work with. Let's actually try to do code review at the same time.” And make sure that we're on top of our software, actually cleaning it up a bit And making sure it's done in a scalable way.Cole [00:44:54]: I think building on that, the idea of, you don't have to look at code, I think is generally a bad idea. And the meme that I have for thatWalden [00:45:03]: What timeline, all right, is Do you think that statement will be true on?Cole [00:45:06]: I think probably for a while it'll be true that you should continue to look at your code. A problem that I see a lot of teams run into that I work with who are embracing AI native, AI first coding, is The meme that I have is that your code base regresses to your worst engineer, because that engineer who is, very gung-ho about AI and is not auditing their code, their pattern starts cementing into the code, and now the AI is referencing their patterns. And so now their if/else block that, is 20 if/elses back and forth, the AI is seeing that as the pattern of how things are done and starts to then exponentially grow this slop. And I find to your point, a pretty good approach to that is having scheduled cleanup, whether by humans or through systems, that are looking for duplication. They then address that. You'll end up with like 12 helpers for how to format a date. And you need to address that, because otherwise it will continue to sprawl.Swyx [00:46:09]: Within balance, I think it's fine to have some duplication, and then sometimes To have garbage collection, right? Yeah. The What I've been, talking about with a lot of engineering leaders is that you want to be very strict about the boundaries between modules, and it's your job as an architect, as a CTO, whatever, to say like, “Okay, here's the hard contract between you guys and you guys. Whatever you do inside this black box is your business. You do whatever. But between these guys, let's be, really damn clear, and any movement must be signed off by a human or me,” or. Then, and like that's that. I don't know if you have any other modifications or advice.Walden [00:46:44]: Well, I guess generally on the topic of, where humans can be useful, I found that ‘cause, some of these, really deep infra problems, sometimes just having a human that just has, really deep expertise can make a big difference. I've actually seen this come into play when actually building agents. So we've had a few friends now, try building their own coding agents, and I think one same problem that I recurringly heard a lot of them run into was this problem of like, “Oh, Grep is really slow on our agents' machines.” And so a lot of them, I assume because they're using AI and they themselves don't have, super deep infra background knowledge, say, “Okay, we're going to go build our own custom Grep index. It's going to be really fast,” and use that as a way around this problem. When we ran into this problem About like, maybe like a year and a half ago when we were, in the early days of building Devin, we obviously didn't have AI then. We just asked our, how to, how to do this. You can just swap out a new Grep index, so.Infrastructure Details: Grep, File Systems, and SandboxesSwyx [00:47:45]: What do you mean you hand-coded Devin? What?Walden [00:47:48]: It's like, can you believe we hand-wrote this code? And we had, our infra people who are really amazing, they were looking into it and they're like, “Oh, what? We realized that actually the root cause of this problem is actually super simple, but like fine-grain detail,” which is that a lot of these virtual machines actually underlying them don't use real file systems. They use these, network file systems where things are actually cached over the network actually in S3. So when you're Grepping, you're actually making network calls Every time you're doing these things, and that's why Grep is extremely slow on these machines. And so again, goes back to, what is all of the crazy infra work that we had to do to actually get these machines working. If you try to do this yourself, there are tons of small details like this, and so we had to eventually go swap out that network file system. ButSwyx [00:48:35]: I think there's a write-up about it, right? Silas did one about the virtual file system.Walden [00:48:38]: Oh, that was a whole other thing. TheSwyx [00:48:39]: Oh, that's a different thingWalden [00:48:40]: The BlockDev file storage formatSwyx [00:48:42]: I'll bring it upWalden [00:48:42]: Which is, a file system format that we built so that the VMs could be spun up and down very quickly. Basically, the intuition behind this is-Imagine you have, a terabyte of disk, and your agent only, wrote, a hundred lines of code on top of that disk. How long does it, say, take to, save and re-bring up that disk? And most systems, because you're not optimizing for this case, it's just, on the order of a terabyte of work because you have to Save all of that and bring it back up. In our system, we try to build a file system that incrementally builds on top of each other. So every time you save and bring the machine back up, you're only doing work that is proportional to effectively the diff in the file system. And so this, shaves off a lot of time in the boot-up process of Devin. I think we This is actually now outdated. We have a newer system inside of Devin. But yeah, there's a lot of tiny details you have to get right here to actually get the day-to-day experience of Devin to be good.Swyx [00:49:39]: It's, not technically agents, but it is agent infra, and when you sell an agent as a company, you sell agent plus agent infra.Walden [00:49:46]: At least the way we do it be And the other The nice thing about having the agent infra being done together is, you We get to deploy Devin in whatever environment we want now. We don't need to wait for some underlying infra provider to also go and support VPC or on-prem or FedGovCloud, for instance. So we can actually go and figure out, okay, since we own the infrastructure, how can we get that set up for you?Cloud Providers: Modal, Daytona, and Enterprise SandboxesSwyx [00:50:12]: Whereas you're Cloudflare dependent.Cole [00:50:15]: so Cloudflare runs the control plane. The sandboxes, Modal is supported. A contributor just added Daytona. E2B is on the roadmap, and I think there's an abstraction in place that if any contributor wants to add a new provider, they can add that in.Walden [00:50:32]: Well, what are, How are the customers you work with Do they generally try to then go set up a contract with another one of these third-party providers? Do they try to do the VMs in-house?Cole [00:50:44]: most of them I see using Modal. I think Modal has a greatWalden [00:50:48]: Shout out Modal.Swyx [00:50:48]: Shout out Modal.Cole [00:50:50]: I think Modal has a great offering. It captures all of the sandbox pieces you need, snapshots being a pretty big piece of that, and given that they also offer GPUs, I think it's a pretty nice offering as a whole.Swyx [00:51:04]: no debate there.Walden [00:51:07]: Modal is great, especially, I think their container offering is, the most natural, and so especially if you are willing to, forego, the full VM requirements Modal is, a really vast place you can spin something up on.Swyx [00:51:20]: Is there a point So Modal's very Python, and I feel like most workload, has really shifted to JavaScript. I don't know if you guys Get the same feeling. So, okay, when I started Landspace and IE and all these things, I was like 50/50 Python and JS, right? That's roughly. I think that's wrong now. I think JS has won. I don't know if you guys Like, I Maybe I'm overstating it, and maybe for cognition, there's, C# and Java and what have you. But for, new greenfield apps, do you feel that Do you get that sense? Does it matter?Cole [00:51:52]: I think that most of the libraries that I see in this space are Python native first, especially in theCole [00:51:58]: Observability space. That said, I think that there is a pretty big appeal of having your entire system in one language. Especially when you have both your frontend and backend communicating, you can have one central type Which is very nice.Swyx [00:52:11]: That's my case against Modal, which is Then you have to run JS. You can run JS inside Modal. It's just, one extra step That, isn't native to the runtime. I don't know ifWalden [00:52:22]: I don't knowSwyx [00:52:23]: Reviews. Do you have numbers? I don't know.Walden [00:52:25]: the one thing I don't like about Python is whenever AI, whenever it writes Python, it always does, the weirdest patterns, andSwyx [00:52:32]: Oh, because it's, mixing two and three or what?Walden [00:52:34]: I think it's something mixing two and three, yeah. The I don't know if you see this. It always tries to do, has attribute on objects as likeCole [00:52:41]: Oh, my God.Walden [00:52:41]: But it's like But that you shouldn't be doing that. It should error if there wasSwyx [00:52:45]: Because it's training on library code?Cole [00:52:47]: I think it's more of, likeCole [00:52:48]: From what I've seen, it's more of, a reward hacking mechanism where it doesn't want to basicallyWalden [00:52:54]: It'll never error.Cole [00:52:54]: It doesn't want the code to fail. And so it Even when it knows it has the attribute, it'll call getattr on a, and for a lot of my clients who have moved towards more autonomous coding, we've put that in as a lint rule That if you do getattr, your pull request is going to fail.Slop Signatures: Comments, Backwards Compatibility, and TypesSwyx [00:53:12]: Ooh, this is a fun topic. Can you tell me more about this? What else is a sign of AI coding that you have to put guards in?Walden [00:53:21]: So we were talking just before this about Opus 4.7. One of the things this new model likes to do is it writes lots of comments. Not like, it'll, comment every line, but it'll write, paragraph, PRDs, on top of every function. But I will say, to its credit, these aren't slop, descriptions like they were before. “Oh, here's what this function does.” It's like, “Oh, here's actually the r

In the latest Confluence Mailbag, Bill O'Grady and Mark Keller revisit their long-held forecast that US hegemony is in decline and consider what a return to a multipolar world order could mean for investors, outlining the shifts and surprises that may shape the evolving geopolitical landscape. The discussion examines the underappreciated economic risks of the Iran conflict, the implications of a 100% debt-to-GDP ratio, and the factors that could challenge their bullish commodity outlook, before closing on a cautionary read of narrowing market breadth as a signal that AI momentum may be nearing its peak.

What is the potential for copper mineralization in the northern Peruvian Andes?  Could uranium be important in the future of South America?   Today's episode features two of the top SEG 2025 Student Podcast Challenge entries.  First, we are featuring the third place team from the competition, the students at the National University of Engineering in Lima, Peru. SEG 2026 Student Podcast ChallengeChapter 1: The potential for copper mineralization in the northern Peruvian Andes: Support for the sustainable green energy transitionNational University of Engineering in Lima, Peru.Hosts,  Milagros Del Rosario De la Cruz Chanco and Erick Ronaldo Romani Pongo  Production Team, Jean Pierre Avendaño Quispe, Felipe Ramiro Robles Salvador, Antonio Chavez Anccasi, Nicolas Valentino Bances Camacho, Jhonny Angelo Urbano Ramos, Lorena Naydelin Rojas Hernandez, Jerry Junnior Ramirez Guadalupe We address Peru's role in the global energy transition and its relevance as the world's third largest copper producer, with 10% of the world's reserves. The southern region dominates production, while the north, despite hosting important projects, remains underdeveloped due to socio-environmental conflicts, lack of infrastructure and a historical bias in exploration. Geologist Pedro Reyes proposes three strategies to reverse this situation: expanding exploration in poorly studied areas, analysing geological transitions between epithermal and porphyry deposits, and evaluating new mineralised styles in the north. He also stresses that the success of these projects depends not only on technical aspects, but also on adequate social management. Finally, he emphasizes that the future of the sector depends on innovation and the training of new generations capable of discovering and exploiting Peru's enormous copper potential, especially in the northern Andes.Chapter 2: Uranium in Latin America: Powering the Future?University of El Paso TexasHosts,  Paola Salas, Aaron Atkins and Bardo Tavizon Editor, Daniel Castano MadrigalIn this episode Paola, Bardo, and Aaron, representing the SEG Student Chapter at UTEP, dive into the exciting possibilities of uranium in shaping the region's energy landscape. Their discussion highlights its vital role as a low-carbon alternative in our global energy mix. While it's true that the public often associates nuclear energy with past disasters and weapons, the hosts shine a light on the technological advancements that are making nuclear energy safer and more sustainable today.The conversation shifts to the immense potential of Latin America, with Brazil, Mexico, and Argentina standing out as key players due to their uranium reserves and growing interest in nuclear power. Yet, they also address the challenges ahead, including environmental concerns, political instability, and public scepticism. The presenters stress the importance of responsible mining, open communication, and investment in education to tackle these issues. In the end, they present uranium as a promising avenue toward a cleaner energy future, provided we approach its development thoughtfully and inclusively.SEG Minerals - Discovery to Recovery  theme music is Confluence, by Eastwinds.EastwindsCome join us in Salt Lake City, Utah for SEG 2026, September 30th to October 3rd. You can expect world-class technical content, including iconic ore deposits and the geological processes of North American Cordillera. The program balances applied case studies, framework geology, and technological innovation. The conference offers a unique opportunity to connect, learn, and help shape the future of economic geology. See you there.

Miranda Walker Jones, CEO of the Little Bit Foundation, joins Megan Lynch. She says the search is on for over 500 students who remain unaccounted for following the May 2025 St Louis tornado. They're scouring records to see where these students ended up when they stopped showing up to St Louis Public Schools and Confluence.

Get more from the experts our community loves. There is a reason Jacob Diaz and Liev Dalton are community favorites. Their monthly Terrain Wellness Club calls have become a staple for our members, providing a space for interactive learning, presentations, and terrain-based health deep-dives that you won't find anywhere else. Become a Platinum member of The Way Forward Community today to see why these calls are the highlight of the month.Use code FWRD for 10% off Beyond Terrain Academy.Diseases like Lyme and mold illness do not work like they told us.Liev Dalton and Jacob Diaz join me on this episode to discuss what happens when terrain-based thinking collides with chronic diagnoses, parasite cleanses, and the wellness industry's obsession with magic bullets. Both of them walked away from systems that promised answers, Liev from licensed therapy, Jacob from organized religion, and ended up somewhere most practitioners never reach. Liev is a biochemist-turned-terrain educator whose work focuses on unlearning modern misconceptions and returning to simplicity. Jacob is a terrain-based Naturopathic Physician practicing in Queens, NYC, and the creator of the UnderCoverVirologist platform.Our conversation moves through Lyme, mold, AIDS, Crohn's, herpes, and the diagnostic loopholes that keep people cycling through tests until they find one that sticks. Along the way: why antibiotics appear to work, what helminth therapy reveals about deworming, and why translocation gets mistaken for transformation.Underneath it all is a thread about faith, coherence, and what changes when you stop trying to fix yourself.You'll Learn:[0:00] Introduction[7:53] The Jesus message that arrived mid-podcast[14:38] My daughter throwing up coagulated blood through a German new medicine lens[23:53] The Mandela effect, the black raven, and why the Bible keeps changing[40:09] The cat with four white paws and what suffering actually means[47:24] Praying with the cop who pulled me over for going 74 in a 55[55:03] How Liev tried to disprove Kaufman and ended up unleashed by his professors[1:08:31] Why boiling toxic water works, and what Pasteur got fundamentally wrong[1:26:52] Why chronic Lyme is a made-up diagnosis, and mold only heals in the forest[2:10:38] What herpes, AIDS, and STDs actually are, and why the cover story held[2:33:54] Why removing parasites causes disease, and what fenbendazole really doesRelated The Way Forward Episodes:Rethinking DNA: Examining the Evidence featuring Dr. Tom Cowan | YouTubeResources Mentioned:Dissolving Illusions by Suzanne Humphries | BookBitten by Kris Newby | BookThe Emperor's New Virus | DocumentaryFind more from Jacob and Liev:Jacob Diaz, Terrain U.V. | WebsiteLiev Dalton, Beyond Terrain | Website | YouTubeFind more from Alec:Alec Zeck | Instagram | XThe Way Forward | InstagramDonate to The Way Forward here.The Way Forward is Sponsored By:PaleoValley: 100% Grass-Fed Bone Broth Protein is a nutrient-dense, easy-to-digest source of collagen and essential amino acids. Sourced from grass-fed cows, this protein powder provides the building blocks for healthy joints, skin, and gut function—without fillers or artificial ingredients. Support the show and claim 15% off your PaleoValley order!Reconnect with the earth's natural charge and move naturally by using code FWRD10 for 10% off at Earth Runners.New Biology Clinic: Redefine Health from the Ground UpExperience tailored terrain-based health services with consults, livestreams, movement classes, and more. Use code THEWAYFORWARD (case sensitive) for $50 off activation.The Way Forward members get the $150 fee waived.

What does AI transformation actually look like inside one of the world's largest engineering organizations? At Team '26 in Anaheim, I recently sat down with Jason Andrews to unpack how Cisco transformed decades of fragmented tooling, disconnected workflows, and spreadsheet-driven operations into a unified system of work built around Jira, Confluence, Jira Service Management, automation, and AI-ready workflows. And honestly, this conversation felt refreshingly practical. Jason oversees engineering operations across Cisco Networking, a business unit with around 22,000 engineers and product managers representing roughly $40 billion in annual revenue. So when he talks about transformation, this isn't theory. This is operational change happening at enterprise scale. We discuss how Cisco consolidated more than 85 Jira instances, reduced tooling spend by 54%, and accelerated reporting by 40x while creating a far more scalable engineering organization. But as Jason explains throughout the conversation, the real challenge was never the technology itself. It was getting teams to rethink how they wanted to work moving forward rather than simply migrating years of technical debt into modern systems. One of the strongest themes in this episode is the difference between transformation and migration. Jason explains why organizations often fail when they focus only on moving systems rather than changing workflows, behaviors, and operational culture at the same time. We also dive deep into AI adoption inside engineering organizations. Jason shares how Cisco is already seeing significant productivity gains from AI-assisted development, why organizational context matters so much for enterprise AI success, and why he believes the industry is still massively underestimating how much structured data and workflow consistency AI systems actually require. Along the way, we unpack scenario planning in the AI era, why annual planning cycles are becoming increasingly fragile, and how leaders can move from rigid long-term roadmaps toward more agile operational playbooks capable of adapting to constant disruption. There's also a fascinating discussion around the so-called "SaaS apocalypse," the limits of AI-generated software, and why Jason believes humans will remain central to enterprise operations for years to come, especially in organizations managing millions of lines of legacy code and decades of accumulated institutional knowledge. If your organization is currently navigating modernization, operational complexity, AI adoption, or large-scale systems transformation, this episode is packed with lessons learned from the front lines of enterprise change. And perhaps most importantly, Jason offers a reminder that AI alone is not the strategy. The real opportunity comes from reducing friction, improving context, and helping teams spend more time solving meaningful problems instead of manually stitching systems together.

What does it mean to be a geologist and an explorer? With introductions by Joy Carter, this is the first of three special episodes.  We hear from two individuals with a rich history in geology and exploration, how the industry has changed throughout their careers and their advice to geologists. These episodes were top entries from the Society of Economic Geologists' 2025 Student Podcast Challenge.  The 2026 competition is now underway! Submissions are due August 21, 2026.  For information check out the SEG website SEG 2026 Student Podcast ChallengeChapter 1:  From Field to Verse: Exploration GeopoetryUniversidad Central del EcuadorHost  Stalyn Paucar Cohosts and production Eslendy Zurita and Dálember Vallejo Martin Litherland, born in 1945, had a remarkable career as a geologist. After earning his PhD from Liverpool University in 1970 for his research of Dalradian rocks in Scotland, he joined the British Geological Survey. This role led him to explore vast, uncharted regions of Africa, and South America. In Bolivia he ventured into the legendary “Lost World” of Sir Arthur Conan Doyle; in Ecuador he led the Cordillera Real Project. His efforts in mapping the Cordillera Real revealed unexpected geological un-Andean features that challenged conventional knowledge. He wrote many scientific papers, memoirs, and geological maps, and in 1993, Queen Elizabeth II honored him with the The Most Excellent Order of the British Empire. Throughout his career, he sometimes felt limited by the formal style of scientific writing, which focuses on data and analysis rather than personal expression. After retiring, Litherland found a new passion in poetry, using it to convey not only his deep connection to geology but also his reflections on various aspects of life.Chapter 2: From Outcrop to Ore DepositUniversity of British Columbia Host Maya SaldanhaWelcome to From Outcrop to Ore Deposit, the episode where we dive into the world of economic geology: research, fieldwork, and the people shaping the next generation of geologists.Maya Saldanha is joined by Dr. Kenneth Hickey, the Director of UBC's field school and an expert in ore deposit geology. We'll chat about his journey from working at the Karangahake mine in New Zealand as a fresh grad to running field courses in the Okanagan Valley, in British Columbia, Canada. Ken shares why field-based learning is so important, how geoscience education is evolving, and what it really takes to prepare students for the fast-changing world of mineral exploration.If you're curious about how geology is taught, what makes a great field school, or how we bridge the gap between academia and industry, this one's for you. Let's get into it!Music is ‘Jamcito - Cumbia Deli' from Youtube Audio LibraryTheme music for SEG Discovery to Recovery is Confluence, by Eastwinds.Eastwinds Come join us in Salt Lake City, Utah for SEG 2026, September 30th to October 3rd. You can expect world-class technical content, including iconic ore deposits and the geological processes of North American Cordillera. The program balances applied case studies, framework geology, and technological innovation. The conference offers a unique opportunity to connect, learn, and help shape the future of economic geology. See you there.

Steve Nison shares how he discovered Japanese candlestick charting techniques in the 1980s, translated Japanese literature, and successfully applied these methods in trading. He explains candlestick construction, the importance of context, and combining patterns with other technical indicators for better signals. Steve also emphasizes strict risk management through protective stop losses. Despite market evolution and the rise of AI, he affirms that candlestick principles remain relevant, as human emotions like fear and greed continue driving markets. https://tradingnut.com/steve-nison/ - Steve's Links

In this episode, Confluence reviews the Asset Allocation rebalance for the second quarter of 2026, featuring a brief economic analysis and insights on asset class and security selection for the firm's Asset Allocation portfolios. Joining the podcast to recap the rationale for this quarter's changes is Kaisa Stucke, analyst and chair of the Asset Allocation Committee's quarterly investment meetings.

This episode comes straight out of a real-life meeting at Confluence.Something became unmistakably clear to me there — what it looks like when a community forms organically. Not managed. Not engineered. Not pushed into existence.But something that actually converges.Confluence itself is a living example of this. You can feel the difference when you're in it. People aren't being organized… they're finding each other.And that stands in sharp contrast to so many of the movements we see today — built, structured, and directed from the outside in.How Do You Know the Difference?There's a real distinction between:something that's growingand something that's being assembledIn this episode, we'll look at how to recognize that difference in real time.Because it's not always obvious… especially when engineered movements borrow the language and appearance of something real.Why Convergence Matters NowOrganic convergence may be the most important thing we can be doing right now.You can't force and engineer connection or put people into structures.But allowing something real to form through clarity, resonance, and shared seeing, that's where the real magic happens.Special Guest: Dawn LesterI'm joined by Dawn Lester, who I had the pleasure of meeting in person at Confluence. Here's our cosmic and unexpected meeting in the San Antonio airport!!Dawn is a master at understanding how things actually come together. She's best known for her writing and research in the alternative health arenas, but she has a gift for convergence — growing community through truth and alignment.In this episode we'll explore:what she sees about real vs engineered communityhow convergence happens (and how it doesn't)and what makes something hold without being forcedIt's subtle and easy to miss… until you see it and can't un-see it.ConvergeIt's what happens naturally and organically. How can we not interfere with it?Join us live to find out and be part of the conversation.The End of the False Self Course: https://www.bethmartens.com/the-end-of-the-false-selfDiscover other deprogramming and archetype courses at www.bethmartens.comApply for a zero-cost, one-on-one chat about working together: https://www.bethmartens.com/awaken-your-journey-archetype-applicationFind out your King Hero Archetype in ten minutes: https://www.bethmartens.com/king-hero-archetype-quiz-sign-upApply to become a House of Free Will Member: https://www.bethmartens.com/house-of-free-will-applicationDo a starter online course: Deprogramming 101 or Find Your Sacred Purposehttps://www.bethmartens.com/deprogramming101https://www.bethmartens.com/find-your-sacred-purpose-online-course ***MORE FROM BETHSign up to take a 5-minute King Hero's Journey archetype quizApply to become a member of the House of Free WillRumbleKing Hero Telegram ChannelTwitter (X)InstagramSign up for a Hero's Journey Archetype ReadingOrder a copy of my book, ‘Journey: A Map of Archetypes to Find Lost Purpose in a Sea of Meaninglessness'Donate by PayPal if you're inspired

What happens when AI stops being a feature and starts reshaping the very craft of design itself? Live from, I sat down with Charlie Sutton for a conversation that went far beyond product interfaces and pixels. As Atlassian unveiled its latest AI ambitions around agents, context, and the Teamwork Graph, Charlie offered a fascinating look at the human side of that transformation and why design may become even more important as AI becomes embedded into the way we work. Charlie shared how Atlassian approaches design at scale across products like Jira, Confluence, Loom, and Rovo, explaining why every interaction should feel intentional and cohesive, even when built by hundreds of people across dozens of teams. But this conversation quickly moved into much bigger territory. We explored how AI is changing the relationship between designers, developers, and business teams, and why the traditional barriers between idea and execution are rapidly disappearing. One of the most thought-provoking parts of the discussion centered around democratization. Charlie argued that while AI tools have dramatically lowered the floor for creativity, they have also raised the ceiling for what users now expect from software experiences. Anyone can prototype an app today, but expectations around quality, coherence, trust, and usability are climbing just as quickly. We also unpacked the growing shift from prompting AI to delegating work to AI agents. Charlie explained why assigning work to agents increasingly resembles managing human teammates, from defining goals and success criteria to understanding strengths, limitations, and context. That naturally led us into a deeper conversation about trust, transparency, and why users must always feel they can "pop the bonnet" and understand what AI systems are doing on their behalf. Another major theme throughout the episode was context. Charlie shared why Atlassian sees organizational context as one of the defining challenges of the AI era and how the Teamwork Graph is helping connect people, projects, conversations, and knowledge across the company. He compared this moment to the first time many of us used Google search and suddenly realized the scale of what was possible. We also discussed how AI adoption is unfolding differently from previous technology waves. Instead of adoption trickling down from hardcore technical users, Charlie is seeing rapid experimentation from marketing, HR, and design teams looking to reduce repetitive work and communicate ideas more effectively. Even his own mother, he joked, has become an AI power user before he has. From AltaVista nostalgia and Ask Jeeves memories to serious conversations about the future of human creativity, this episode captures a rare and honest perspective on where design, collaboration, and AI may be heading next. How will organizations balance personalization with shared experiences as AI becomes embedded into every workflow, and what role will human creativity play when everyone suddenly has access to the same powerful tools? Please check the partners of the Tech Tech Talks Network Learn more about the NordLayer Browser Visit Denodo.com

What happens when one of the most iconic teams in Formula One decides to rethink how work gets done behind the scenes completely? Last year, Atlassian Williams Racing made headlines when Atlassian entered Formula One as both title partner and technology partner. At the time, many people saw the partnership as another high-profile sponsorship deal. But over the last twelve months, something much bigger has been unfolding inside the Williams organization. At Team '26 in Anaheim, I sat down with Andrew Boyagi and Matt Harman to unpack how AI, data, workflows, and organizational transformation are reshaping life both at the factory and on the grid. This conversation goes far beyond racing. Matt explains how Williams is reducing the time between "idea to track," compressing development cycles so upgrades arrive at race weekends weeks earlier than before. One striking example involves reducing front wing lead times by a factor of three through parallel workflows and better collaboration, allowing performance gains to reach the circuit three race weekends sooner. Andrew shares how Atlassian's system-of-work philosophy is being applied in one of the most data-intensive environments on earth. We explore how tools like Jira, Confluence, Loom, Rovo, and Teamwork Graph are helping engineers, strategists, operations teams, and factory staff make faster decisions with less operational friction. We also discuss how AI is changing engineers' roles, why organizational context matters more than raw intelligence, and how Formula One teams balance human instinct with AI-driven precision in race strategy decisions. Matt offers fascinating insight into how AI helps teams process decades of historical race data in real time while still relying on human judgment in critical moments. Along the way, we explore the cultural transformation underway at Williams, including the shift away from endless meetings toward faster, outcome-focused collaboration. Matt explains how tools like Loom and Confluence are helping teams make decisions more efficiently while spreading knowledge more effectively across specialist departments. Andrew also reveals some eye-opening metrics from the partnership so far. Since rolling out Atlassian's Teamwork Collection, teams have reportedly increased throughput by 83%, while low-value meetings have been reduced by 863 hours in a single month across 200 people. Perhaps the biggest takeaway from this episode is that Formula One may actually be a perfect reflection of the challenges facing every modern business. As Andrew puts it during our conversation, Formula One is ultimately "an enterprise performance problem," just operating at 300 kilometers an hour with millions of people watching every weekend. If you've ever wondered what enterprise transformation looks like when milliseconds matter, this episode offers a fascinating look inside one of the most ambitious AI and workflow transformation journeys happening anywhere in business today   Please check the partners of the Tech Tech Talks Network Learn more about the NordLayer Browser Visit Denodo.com

This week, Hussam stops by and shares so much love that we're both crying half way through our chat. He has been a part of organizing and supporting the YYC Peace Table and the delicious, YYC Peace Brunch which is happening May 31, 2026 at The Confluence in Calgary. He shares portions of his journey as a Palestinian man living in Canada. This includes him being arrested and deported unjustly by the Canadian government. Through our conversation we both started to feel the weight of everything we were chatting about. There's a moment when our rage, sorrow, joy, and love all come together and we pause to feel. Pause to reflect and grieve for the bleeding world around us. For our own wounds. Pause to regain some strength so we could keep moving forward and not get lost in the horrors alone. Thank you for being you and for attempting to share your love every day in every direction. That kind of humanity is something I want to strive for.Check him out on instagram: @peacetableyyc

AI agents are reshaping enterprise workflows, increasing the importance of organizational context and connected data. Atlassian CEO and co-founder Mike Cannon-Brookes joins Bloomberg Intelligence senior software analyst Sunil Rajgopal to discuss how Atlassian is embedding AI across Jira, Confluence and service-management tools through its Rovo platform and Teamwork Graph. “The future is about human and agent collaboration,” Cannon-Brookes says. The discussion also covers enterprise AI adoption, developer productivity and API-driven software infrastructure.

"This segment is sort of ambiguous - am I listening to the Lech or to the Danube? Maybe both, or maybe it's all Danube, and “Lech” is just what we called it before it got there. I worked on that moment, and I looked at what that could mean for the river water, which had come from all these different places, with all these different sounds. "One of the included photos is a bird's eye view of the two rivers, side by side - they really appear independent in that photo. The satellite timelapse is different - first, the orientation and curve of the Lech make it feel like it's contributing to the Danube, visually. Most strikingly, in the timelapse, color changes in the Lech appear to continue into the mixed river - when the Lech changes color, the water in the Danube which came from the Lech also changes color. This may simply show that the two rivers don't mix right away, but it got me thinking about perspective, direction, and naming: There is a known end point of the Lech, but the Danube seems to exist before and exist after. "When the Lech ends, the Lech water continues, but now named Danube. This process is continuing constantly, and the water that meets the Danube could have come from many different places, and gone through many different experiences - those experiences show up in the variety of colors in the timelapse, and in the variety of sounds collected for this project, certainly."I thought, I may be able to express these through music theory, through melody. Better than words, anyway. What's in a name…"The piece itself is a collection of melodies, recorded on 9 different musical instruments - all the instruments are playing distinct melodies, and every melody leads to the same musical pitch. This is the many waters all leading to/becoming the Danube. "The field recording is also played back several times at higher and lower speeds over the course of the piece, sort of a like a slow melody of its own - those also lead to a final note: the recording played back at the original speed. "Hearing that last note, the drone, the tonic, I wonder if it's possible to know all the different ways that an instrument could have gotten there. We see the Danube and call it Danube, but there may be some awareness of how the water got there, too. "For those interested:The music theory behind the scenes here is something I've been working on with some friends here in Seattle - the term we are using is “nonatonic harmony” (which translates to “harmony derived from a 9-note scale”). Since I recorded the melodies individually, one by one, and then stitched them all together after, there might be an argument that this is more accurately “polymodal music”, but I'm more excited about this 9-note system, so that's why I'm considering it in those terms. "Here's some more explanation -It's common to refer to musical pitches by letters in the alphabet - A B C D E F G, then wrapping back around to A. That's seven distinct notes - scales that have one of each letter are considered “heptatonic” (which translates to “seven-tones”). In this piece, I was working with these notes: A Bb B C D E F F# G. That's nine notes all together, so, “nonatonic”. By the way, since there's only seven letters in this standard alphabet system, the sharps (#) and flats (b) are added to existing letters in order to make new notes, between the letters. "There's a few available perspectives on this arrangement of notes - one is to see it as 9 totally distinct notes. There are some moments in this piece that feel like that, the moments that are dissonant, because you have two different B notes (B and Bb), or two different F notes (F and F#), and they clash. "Another perspective is to play the heptatonic modes which are nested inside the nonatonic scale (this is the polymodal perspective). That original alphabet scale (A B C D E F G) can be played differently to lead to certain notes (“leading to certain notes” is one definition of many for a “mode”). Using those same pitches (A B C D E F G), the melodies that use the notes in such a way to lead to D are called “dorian”, and the melodies that use the notes in such a way to lead to E are called “phrygian”. If we were to use phrygian and dorian melodies, but instead have them all lead to A, we would have to amend the alphabet system a bit, using sharps (#) and flats (b). In the nonatonic scale listed above, we can find an aeolian mode (using the notes A B C D E F G), a dorian mode (using the notes A B C D E F# G), and a phrygian mode (using the notes A Bb C D E F G) - which each lead to A. "In practice, this system allowed me to navigate to the final note of each melodic phrase with more options, maybe specifically with two more options (either B and either F). It also introduced more dissonance, which is a characteristic of a lot of music, maybe music in general - I should note that this system isn't particularly innovative in itself, we're just putting words to something that happens already in a lot of music. How useful is that? Maybe, if only so that we can talk about it."Section of the river Lech reimagined by Nicolo Scolieri. -------Flow is a creative exploration telling the story of a river through the power of sound. The project is a collaboration between the University of Padova and the University of Würzburg, with support from Cities and Memory. Explore the full project at https://citiesandmemory.com/flow.

Enterprises spent the last decade hardening the front door for human users. Now a new class of worker is showing up to the same applications, asking for the same data, and acting on someone else's behalf. Shreyans Mehta, Co-Founder and Chief Technology Officer of Cequence Security, joins ITSPmagazine to talk through what changes when ten or more agents are operating in your name across email, code repositories, Confluence, Salesforce, and ServiceNow at the same time. For Shreyans Mehta, safe enablement is the central question. Consumer chatbots normalized point-to-point connections into personal inboxes, but enterprise agents are reaching into crown-jewel systems where blanket access is not an option. Cequence Security has spent years protecting applications and APIs for telcos, financial institutions, and retailers, and that history shapes how the team is approaching the agentic shift: how do you let the right work get done without handing over the keys to the building? Identity alone is not the answer. Agents can hallucinate, can be prompt-injected, and will go to great lengths to complete a task. Cequence Security addresses this with what Shreyans Mehta calls an agent persona, a dynamic, job-description-driven scope that limits an agent to exactly what its role requires. An email assistant gets read access and a calendar check, not the ability to send or delete. The job defines the permissions, and the permissions follow the agent through the Cequence AI Gateway platform. This is a Brand Highlight. A Brand Highlight is a ~5 minute introductory conversation designed to put a spotlight on the guest and their company. Learn more: https://www.studioc60.com/creation#highlight GUEST Shreyans Mehta, Co-Founder and Chief Technology Officer, Cequence Security LinkedIn: https://www.linkedin.com/in/shreyans-mehta-37a529/ RESOURCES Learn more about Cequence Security: https://www.cequence.ai/ Are you interested in telling your story? ▶︎ Full Length Brand Story: https://www.studioc60.com/content-creation#full ▶︎ Brand Spotlight Story: https://www.studioc60.com/content-creation#spotlight ▶︎ Brand Highlight Story: https://www.studioc60.com/content-creation#highlight KEYWORDS Shreyans Mehta, Cequence Security, Sean Martin, brand story, brand marketing, marketing podcast, brand highlight, agentic AI, agent identity, AI agents, agent persona, API security, non-human identity, safe enablement, enterprise AI, prompt injection, MCP, AI gateway Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

This special edition of the Confluence Leadership Podcast was recorded at the C26 Leadership Conference in Saint Louis, MO and features Mac Lake and Bo Noonan.If you would like more information about Confluence Churches, please visit our website at confluencechurches.org

For several years in my forties, I swam in the ocean each morning. The water was cold when we dove into the Bay and often times it would take a while before my strokes would find the rhythm of the waves in order that I wouldn't swallow too much water whenever I turned my thermal cap covered head to take a breath as I watched the city lights in the dawn of early morning.This past week has been full. We went to our daughter's and son's gathering in Texas, where over 1000 people gathered for Confluence, and yesterday I sat with my sister through her 4-plus hour appointment for her first chemotherapy infusion.Listen in as we explore just how our job is to ride the waves of life.Thank you for being here; you matter.I am offering sessions on Tuesday mornings. If you want an elder to hold space for you and reflect on your amazingness, sign up on my website. I am always happy to hear from you.You can reach me at terces@tercesengelhart.com, and I will reply. Additionally, if you would like to order my book directly from me, I am happy to send you a signed copy. Please email me, and I'll send it to you. ($15 plus shipping)If you know of anyone who might benefit from listening in, share a link to an episode with them; in other words, be an invitation to join us. Get full access to Terces's Substack at engelhart.substack.com/subscribe

Joel and Yerasimos return from Confluence — five days in Bandera, Texas, with eleven hundred people and thirty-plus members of their own community — and unpack what only embodied gathering can teach: that touch, presence, and shared fire are not luxuries but necessities, and that digital connection is a thin slice of the long arc of being human. The conversation widens from there into agency itself — the courage to make different choices, the timelines we collapse and create with each one, the thermostat of self-concept that quietly calibrates the life we end up living. Fortune favors the bold…and the bolder act, almost always, is the smaller one, made today, in the direction of who you actually are.CONNECT WITH USStart the Free 7-Day Self-Esteem ResetWatch Our EpisodesJoin our free Telegram communityJoin our membership Friends of the Truth

Fresh back from Confluence in Texas, this episode is about returning — coming back with something real.I'll share some highlights and adventures from the experience, and what transformation happens when we step out of our usual environments. Patterns loosen, new clarity appears while you're away, but many people wonder how to hold onto it when they're back in regular life. In addition, I have a wonderful returning guest…With Special Guest: Micah EllarsI'm joined by filmmaker, acting coach, and teacher of George Gurdjieff's work, Micah Ellars, to explore the mechanics of false personality and programs. We hear the word all the time, but…What actually are they, and how do they form?What are the clear signs of them, including indecision, crossroads, and relationship friction?Our self-concept says we're one person, but in reality there are multiple “I's”.When they are clearly seen and release begins:identification loosensreactions and triggers lose their gripspace opens for real choice and authentic connectionMicah will also share some stories, examples, and a glimpse into the process we'll be using in:The End of the False SelfCourse starting May 9th!!!The End of the False Self Course: https://www.bethmartens.com/the-end-of-the-false-selfDiscover other deprogramming and archetype courses at www.bethmartens.comApply for a zero-cost, one-on-one chat about working together: https://www.bethmartens.com/awaken-your-journey-archetype-applicationFind out your King Hero Archetype in ten minutes: https://www.bethmartens.com/king-hero-archetype-quiz-sign-upApply to become a House of Free Will Member: https://www.bethmartens.com/house-of-free-will-applicationDo a starter online course: Deprogramming 101 or Find Your Sacred Purposehttps://www.bethmartens.com/deprogramming101https://www.bethmartens.com/find-your-sacred-purpose-online-course ***MORE FROM BETHSign up to take a 5-minute King Hero's Journey archetype quizApply to become a member of the House of Free WillRumbleKing Hero Telegram ChannelTwitter (X)InstagramSign up for a Hero's Journey Archetype ReadingOrder a copy of my book, ‘Journey: A Map of Archetypes to Find Lost Purpose in a Sea of Meaninglessness'Donate by PayPal if you're inspiredFollow the King Hero's Journey Podcast on... Apple Podcasts SpotifyIf we're just meeting...I'm Beth Martens—founder of the House of Free Will, pattern hunter, archetype reader, podcaster, author, coach trainer, and  business coach. My calling has truly been a life-or-death matter. After a decade as a corporate VP in my family's firm, eight transformative trips to India, and a three-year battle with cancer nearly 25 years ago, I turned to archetypes and deep deprogramming work to save my life.Despite doing everything wrong based on limited health knowledge, I accessed the hidden inner roots of what was keeping me sick, stuck, and unconscious. Letting those patterns go changed everything. I went from dying to living almost overnight.Today, I help people who love truth more than their beliefs—people who want to serve with their life's work and walk their Hero's Journey—to deprogram the beast system from within and stop unconsciously feeding the forces that harm us.I host the King Hero interview series, where I spotlight leaders, entrepreneurs, movement makers, and lovers of freedom who are carving new paths in a world that desperately needs them. And I also share my own voice, insights, and stories through my new solo podcast, Beth of Fresh Air.

Boris Berenberg bootstrapped Atlas Authority, an Atlassian partner that resold Jira and Confluence to mid-market companies and built apps on top of the platform, to high seven figures in revenue with 18% net margins, then sold to private equity in May 2022.  A year later he wrote a blog post titled "I regret selling my startup" that went viral inside the exited founder community. 

In today's episode, WLA Communications Director Louis Wertz sits down with Aireona Raschke, who leads collaborative efforts across the West through her work with the Center for Collaborative Conservation and the Western Collaborative Conservation Network at Colorado State University. Aireona gives us a preview of this year's Confluence –a conference designed to support and connect people across the West doing the important, and often challenging, work of collaborative conservation. Whether you plan to attend or not, this is a great conversation about what it takes to bring people together and build solutions that last. More information about Confluence 2026 can be found here.

I just got back from Confluence 2026. This was my fourth year going, and every single time it gets bigger, better, and more impactful. I wanted to sit down and share 5 takeaways that really stood out to me—not just from this year, but from all the Confluences I've been to. - Your vibe attracts your tribe - Conscious, grounded, beautiful people - The divine law is in full effect - Work hard. Play hard. - God is good all the time, all the time God is good   Join me for the show and get a taste of the what the Confluence magic all about. Hope to see you out there next year! In the meantime, come Nov. 5 to 8th we are hosting Exit and Build 6 out the same venue, Mollie Engelhart's Sovereignty Ranch. Tickers are currently on Builder-bird pre-sale through May 1st. https://exitandbuild.com Join Our Free Newsletter Stay updated on ways to live free and get our FREE video on how to Hack Your Habits and 10X Your Goals! https://livefree.academy/newsletter SUPPORT OUR SPONSORS Zano - Privacy Coin with Tokens! Zano is a powerful privacy coin built for real-world use. It allows users to create and transact with private tokens, including stablecoins like Freedom Dollar, a privacy-focused stablecoin pegged to the value of the dollar. You can even bridge transparent Bitcoin into the Zano blockchain and use it privately. Learn more here: https://zano.org/ Wise Wolf Gold and Silver Precious metals in your mailbox = Peace of mind Wise Wolf Gold and Silver's Wolf Pack program ships physical gold & silver monthly with auto-subscriptions. Code livefree gets you free junk silver with your first order! https://livefree.academy/wolfpack CrowdHealth is revolutionizing how we handle medical bills. ✅ No networks. ✅ Transparent costs. ✅ Support from a like-minded community. USE CODE LFA at checkout to get a discounted membership of $99/month for the first 3 months. https://www.joincrowdhealth.com/promos/lfa 

CCP welcomes returning guest Michael Thomsen of Origin 84 from Sydney, Australia and discusses how he prepares to leave his business for long travel by relying on organizational design, documentation, and clear accountability, using Confluence and EOS-style role success criteria to prevent gaps and duplication. They explore perfectionism versus "good enough," emphasizing repeatable standards a team can deliver, protecting integrity, and avoiding preventable mistakes. The conversation shifts to why SOC 2, HIPAA, and ISO 27001 matter as clients face more vendor-risk questions, and how policies differ from procedures by enabling decentralized decisions. Michael explains Origin 84's fixed-fee, services-first model and a "magic quadrant" approach that moves from help desk and IT admin to account management and strategy, using root-cause fixes across all clients. He details standardizing on Microsoft-first tooling (including Entra SSO for Google), vendor-risk concerns, and how certification frameworks drive continual improvement and practical, auditable policies.   00:00 Welcome Back Michael 00:35 Travel Rituals Offline 01:14 Leaving the Business 03:23 Planning Like Military 04:47 Runbooks EOS Accountability 07:22 Perfection Versus Good 13:53 Standards And Certifications 16:32 Policy Versus Procedure 17:56 Building Sticky Services 20:14 Magic Quadrant Strategy 23:16 Fix Root Causes 26:21 Flat Rate Incentives 27:45 Strategy Alignment Limits 29:13 Listening Before Pushing 30:08 Pricing Pushback Story 31:52 Standardize Security Baselines 34:33 Paying for Certification Proof 36:10 Cut Costs via Account Management 36:50 Client Owned Subscriptions 39:21 Microsoft as North Star 41:10 Vendor Risk and Contingencies 47:37 Entra SSO for Google 50:46 ISO 27001 Policy Reality Check 54:57 Part Two Wrap Up

In this month's Confluence Mailbag, Bill O'Grady and Mark Keller examine what Iran's shift to yuan-denominated oil transactions means for the dollar's reserve currency status and why viable alternatives remain elusive. They assess widespread concerns around private credit, weigh the broader economic ramifications of the Iran conflict — including the collapse of just-in-time inventory thinking — and close with a discussion of whether the rotation away from mega-cap growth stocks still has legs.

Mareko & Geoff answer your questions an horse around. Thanks again to Evenheat, Damasteel, Brodbeck Ironworks, Texas Farrier Supply, Indasa, Tormek, Indasa, Maritime Knife Supply and Tormek for the support.Advertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacy

To hear the whole show, tune in live from 9:00 AM - 11:00 AM Monday-Friday. For more sports coverage, download the ESPN630 AM app, visit https://www.sportscapitoldc.com. To join the conversation, check us out on twitter @ESPN630DC and @andypollin1See omnystudio.com/listener for privacy information.

Hour one of Jake and Ben for April 7, 2026: Michigan Wolverines win national championship Top-3 stories of the day Confluence of Real Salt Lake, World Cup and The Masters

The entirety of Jake and Ben for April 7, 2026: HOUR ONE Michigan Wolverines win national championship Top-3 stories of the day Confluence of Real Salt Lake, World Cup and The Masters HOUR TWO Utah Jazz come down home stretch of season Cole Bagley, KSL Sports Bob Casper, Real Golf Radio

There were not many signs of life in Pittsburgh this weekend for the scuffling Baltimore Orioles, who were swept by the Pirates and are headed to to frigid Chicago with ice cold bats. Luke Jones and Nestor discuss with disgust the Orioles lost Easter weekend at The Confluence. The post Luke Jones and Nestor discuss with disgust the Orioles lost Easter weekend in Pittsburgh first appeared on Baltimore Positive WNST.

Convergence? Confluence? Three getting together?For Pookajutsu ♥️Catch us live every Sunday at 14:00 on ⁠https://www.youtube.com/@RPGClinic/videos⁠Blue Sky: ⁠https://bsky.app/profile/rpgclinic.bsky.social⁠Website: ⁠http://www.rpgclinic.com/⁠Wiki: ⁠https://rpgclinic.fandom.com/wiki/⁠Discord server: ⁠https://discord.com/invite/kenG3xu⁠An RPGClinic campaign promises committed storytelling and performances, professional tech, dynamic overlays, and info boxes to keep the system accessible to new viewers. Games swing between comedy and drama at the drop of a hat. There will be laughter. There will be tears. There will definitely be double-entendres.

This week on The Jira Life, we're joined by Ed Gaile of Appfire to explore the intersection of creativity, automation, and the future of teamwork.We dive into the emerging concept of Vibe Coding—what it is, why it's resonating with modern teams, and how it shifts the way we think about building and interacting with tools. From there, Ed walks us through the practical side of innovation: connecting the Rovo MCP server to Jira and Confluence to unlock new possibilities for integration, orchestration, and intelligent workflows.Whether you're experimenting with new development paradigms or looking to push the boundaries of your Atlassian stack, this episode blends vision with hands-on insight in a way only The Jira Life can.Tune in for a conversation that's equal parts inspiration and implementation—and maybe catch a new vibe along the way.The Jira Life=====================================Having trouble keeping up with when we are live? Sign up for our Atlassian Community Group!https://ace.atlassian.com/the-jira-life/Or Follow us on LinkedIn!https://www.linkedin.com/company/the-jira-life/Become a member on YouTube to get access to perks:https://www.youtube.com/@thejiralife/joinHosts:- Alex "Dr. Jira" Ortizhttps://www.linkedin.com/in/alexortiz89/https://www.youtube.com/@ApetechTechTutorials- Rodney "The Jira Guy" Nissenhttps://www.linkedin.com/in/rgnissen/https://thejiraguy.com- Sarah Wrighthttps://www.linkedin.com/in/satwright/Producer:- "King Bob" Robert Wenhttps://www.linkedin.com/in/robert-wen-csm-spc6-a552051/Executive Producer: - Lina OrtizMusic provided by Monstercat:=====================================Intro: Nitro Fun - Cheat Codeshttps://www.youtube.com/c/monstercatOutro: Fractal - Atriumhttps://www.youtube.com/c/monstercatinstinct

Bill O'Grady and Mark Keller tackle some pressing market topics, opening with a nuanced look at how the conflict in Iran might unfold and what current market expectations may be overlooking. They discuss the concentration risk embedded in passive investing and how investors can navigate it, before turning to the shifting dynamics and recent headlines in private credit, including their perspective on the implications for BDCs. The episode concludes with a forward‑looking conversation about whether the rise of artificial intelligence could reshape the financial advice industry.

Tickets are on sale for Confluence 2026. Use code ZECK10 for 10% offThis talk is from the 2025 edition of the Confluence Festival. Platinum Members of The Way Forward get access to all past Confluence talks, as well as 20% off all Confluence tickets. Become a Platinum member here.You have the greatest currency in the world within you… and you can use it to break out of the toxic system we live in.This video is a little different from our usual podcast. I asked Tom Barnett to talk about Natural Law in the 2025 edition of the Confluence Festival, and his presentation called “The Offer” didn't disappoint. His path into natural law, self-sovereignty, and personal responsibility began long before he even knew those words existed. Growing up in Australia, Tom constantly questioned the limits of freedom and democracy, often finding himself in conflict with authority while trying to understand why the world felt so inconsistent and unfair. His background in holistic health, spanning sports performance, nutrition, psychology, emotional patterns, and spiritual lessons, deepened during a long personal battle with chronic fatigue that eventually pushed him to explore consciousness, natural lore, and the deeper laws shaping reality.This presentation explores how the hero's journey applies to modern life, the difference between lawful and legal systems, and why true change may begin with confronting our own inner government. If we want a different world, the first step might be remembering who we actually are.You'll Learn:[00:00] Introduction[12:24] How law, lore, and story all connect[20:11] Why natural law is the "great leveler" and what that means for your standing [27:25] How Tom overcame 20 years of chronic fatigue[44:38] Why going fully private is a trap, and what mastering both worlds actually looks like[50:32] Your name is not you, and the pop quiz that proves it[01:00:45] Ancient knowledge was never destroyed, it's waiting in counter space[01:08:50] The difference between a grounded no and a fearful refusal[01:20:41] Why breathwork is just the beginning, and how to reach the essence beneath intentLearn more about Tom:The Humble Kingdom | WebsiteThe Humble Kingdom | InstagramTom Barnett | FacebookTom Barnett | InstagramFind more from Alec:Alec Zeck | InstagramAlec Zeck | XThe Way Forward | InstagramThe Way Forward is Sponsored By:PACHA Sourdough: The wheat-free, sprouted buckwheat bread that actually digests well. Made with just two ingredients: organic sprouted buckwheat and sea salt. No gums, oils, or fillers.Shop now and use code THEWAYFORWARD for 10% off. Dr. Cowan's Garden helps you boost daily nutrient density with vegetable powders and clean, pasture-raised essentials. Shop now and use code: THEWAYFORWARD for 15% off your first order.

Now is a great time to revisit the Case for Hard Assets, an investment area that's drawing considerable interest these days. Confluence Advisory Director of Market Strategy Bill O'Grady draws on his deep expertise in commodities to explain the asset class and the firm's Global Hard Assets strategy. He outlines the investment team's macro-driven decision‑making process, offers insight into the current portfolio, and shares his outlook for the asset class, highlighting the key factors driving renewed appeal for hard assets in today's market environment.

In this episode, Confluence reviews the Asset Allocation rebalance for the first quarter of 2026, featuring a brief economic analysis and insights on asset class and security selection for the firm's Asset Allocation portfolios. Joining the podcast to recap the rationale for this quarter's changes is Kaisa Stucke, analyst and chair of the Asset Allocation Committee's quarterly investment meetings.

LIVESTREAMING tonight at 7:00pm EST... Join us as we welcome Paul Abbott back to the show for a follow-up conversation about events surrounding the basement shooting of LHO. Book link below... Tune in for a good one!Book Link - https://a.co/d/0djhNiRnPaul's Articles - https://pabbott.substack.com/Paul's Podcast - https://podcasts.apple.com/us/podcast/death-to-justice-the-shooting-of-lee-harvey-oswald/id1835192062Silk CIty Hot Sauce - https://www.silkcityhotsauce.com Use our code GUNMAN for 20% off entire order at checkout! The COLDEST Cup - https://snwbl.io/TLG10 Follow our link to save $10 on every cup ordered!Music By - Lee Harold OswaldA Loose Moose ProductionBBB&JOEBBecome a supporter of this podcast: https://www.spreaker.com/podcast/the-lone-gunman-podcast-jfk-assassination--1181353/support.

In this episode, Todd Reed speaks with Kassy Slaughter about the current state of the construction industry, focusing on labor shortages, the impact of technology, and the importance of company culture. They discuss the challenges faced by the industry, including misconceptions about construction careers, the need for a cultural shift, and the role of data and AI in improving workforce engagement. Kassy emphasizes the importance of creating a supportive work environment and the need for actionable steps to attract and retain talent in the construction sector. Kassy shares about one of her favorite restaurants, Iron Bay in Marquette, MI and talks about her favorite pastime, kayaking. Thank you for listening and please take a moment to subscribe, rate, and review the show on your favorite app.Here's where I ask a huge favor from you, I'm creating a newsletter as a way for you to share your thoughts on the episodes, share guest ideas and for me to give you insight into future episodes, and of course share great restaurants with you, please subscribe at  https://www.graybar.com/podcast#subscribe.Iron Bay Restaurant in Marquette: https://ironbaymqt.com/ To reach Kassy Slaughter on LinkedIn:  https://www.linkedin.com/in/kassy-slaughter-morris-59164020/Learn more about Procore: https://www.procore.com/ On YouTube: https://youtu.be/KJT9ftw3K8I

“When I tell you a story about my body, I cannot separate it from a story about water. And a story about water is also a story about family. And a story about family is rooted in the earth…,” opens Sangamithra Iyer’s Governing Bodies. What does it mean for a memoir to assume the elusive, ever-changing shape of water, to be the story of family but where the notion of family crosses the boundaries of blood, culture, nation and even species? Governing Bodies, as the Whiting judges said in their citation, is “a subtle, meditative exploration on grief and nonviolence, an international and intergenerational voyage through shared histories and a consideration of what we owe to each other and the natural world.” For the bonus audio archive, Sangu contributes a reading of her remarkable essay “Are You Willing?” which originally appeared in the anthology Writing for Animals: New Perspectives for Writers & Instructors to Educate & Inspire. This joins an ever-growing archive of contributions from past guests—from Richard Powers to adrienne maree brown, Forrest Gander to Arthur Sze, Natalie Diaz to Ada Limón. You can find out how to access the bonus audio and about the many other potential benefits and rewards to choose from, when you join the Between the Covers community as a listener-supporter, at the show’s Patreon page. Finally, here is today’s BookShop.