Constructed Futures

Follow Constructed Futures
Share on
Copy link to clipboard

A weekly conversation about the future of our built environment, featuring outside experts and seasoned leaders in construction, architecture and more.

Hugh Seaton


    • Jun 2, 2025 LATEST EPISODE
    • every other week NEW EPISODES
    • 28m AVG DURATION
    • 249 EPISODES


    Search for episodes from Constructed Futures with a specific topic:

    Latest episodes from Constructed Futures

    Michael Latiner: Delivering AI-Powered Business Outcomes for Contractors at Quantum Rise

    Play Episode Listen Later Jun 2, 2025 19:28


    check out Quantum Rise here: https://www.quantumrise.com/

    Connor Schmeling: Making AI Work for Contractors at Quantum Rise

    Play Episode Listen Later May 27, 2025 26:03


    Check out Quantum Rise here: https://www.quantumrise.com/Follow Connor here: https://www.linkedin.com/in/connorschmeling/

    Alex Kelleher: AI Consulting for Contractors at Quantum Rise

    Play Episode Listen Later May 19, 2025 26:30


    Check out Quantum Rise here: https://www.quantumrise.com/Follow Alex here

    Joe Pascal: World Class Facility Commissioning with Facility Grid

    Play Episode Listen Later May 13, 2025 24:52


    Follow Joe Pascal here: Check out Facility Grid here: https://facilitygrid.com/

    AI Briefing Series: Agent Communication Protocols

    Play Episode Listen Later May 5, 2025 39:29


    In addition to MCP, Google, IBM and others have presented protocols and frameworks that will help AI agents talk to each other. These protocols are essential unlocks to getting value out of agents. This hosted briefing walks through the protocols and why they matter.

    AI Briefing Series: Prompting New AI Models

    Play Episode Listen Later Apr 21, 2025 11:41


    Want to get more out of AI? Check out The Link.AI Consulting

    Grant Quasha Decarbonizing Concrete at Eco Material Technologies

    Play Episode Listen Later Apr 1, 2025 28:27


    Check out Eco Material Technologies here: https://ecomaterial.com/Follow Grant here

    Andrew Ackerman: The Entrepreneur's Odyssey

    Play Episode Listen Later Mar 27, 2025 28:42


    Pre-order The Entrepreneur's Odyssey hereIf you do, email him a screenshot of the purchase so he can invite you (or a portco if you're a VC) to his in person sessions here: andrewbackerman@gmail.comFollow Andrew's Socials here:LinkedIn: http://www.linkedin.com/in/andrewbackermanX @AndrewAckermanBlog: http://AsAngelsSeeIt.com

    Richard Bergen: Tech Innovation in AEC at Bergen Wood

    Play Episode Listen Later Mar 25, 2025 24:58


    Follow Richard hereCheck out Bergan Architectural Woodworking here: https://www.berganwood.com/

    Timothy Wingate Jr.: Construction Accounting at  G+F Business & Financial Consulting

    Play Episode Listen Later Mar 20, 2025 21:58


    Follow Timothy hereCheck out G+F Consulting here: https://www.gplusf.com/

    AI Briefing Series: Expanding AI Agent Capabilities with Model Context Protocol (MCP)

    Play Episode Listen Later Mar 17, 2025 24:50


    Check out The Link.AI Consulting at https://agentic.constructionConnect with Hugh on LinkedinHere's a shorter briefing based on the same informationExecutive Summary:Anthropic's Model Context Protocol (MCP), announced in late November 2024, is an open protocol designed to standardize how AI systems interact with external data sources and tools. It aims to overcome the current fragmented landscape of AI integration, where bespoke solutions are often required for each new connection. MCP establishes a universal framework for communication, simplifying development, enhancing AI agent effectiveness through improved context and tool access, and fostering a vibrant ecosystem of AI capabilities. By utilizing a client-server architecture and defining key primitives for data and action exchange, MCP offers a more dynamic and context-aware approach compared to traditional REST APIs. The emergence of MCP registries and marketplaces like smithery.ai further signifies its potential to transform the future of AI by enabling more interconnected, adaptable, and powerful AI systems.Key Themes and Important Ideas/Facts:1. Addressing the Challenges of AI Integration:The current method of integrating AI models with external resources is often complex and requires custom solutions for each connection. "When building AI applications today, each project frequently requires unique, bespoke solutions for how AI processes are constructed and how they connect with necessary data resources." (Introduction)This leads to significant development and maintenance burdens.MCP aims to solve this by providing a universal, open standard for connecting AI systems with data sources and tools. "MCP offers a unified solution to this problem by providing a universal, open standard for connecting AI systems with data sources, effectively replacing these fragmented integrations with a single, consistent protocol." (Introduction)The motivation is to overcome the limitations of isolated AI models "trapped behind information silos and legacy systems." (Introduction, citing source 2)MCP addresses the "MxN problem" by transforming it into an "N plus M setup," where each model and tool only needs to conform to the standard once. "Without a standardized protocol, this results in a complex web of M multiplied by N individual integrations... MCP's approach transforms this into a much simpler N plus M setup, where each tool and each model only needs to conform to the MCP standard once..." (Introduction, citing source 3)By open-sourcing MCP, Anthropic intends to foster collaboration and a shared ecosystem.2. Core Concepts of MCP:Client-Server Architecture: MCP is built on this established pattern. "At its core, the Model Context Protocol (MCP) is built upon a client-server architecture, a well-established design pattern in computing, to facilitate the connection between AI models and external resources." (Core Concepts)Host: The AI-powered application or agent environment the user interacts with (e.g., Claude desktop app, IDE plugin). "The Host is the AI-powered application or agent environment that the end-user directly interacts with." (Core Concepts) It can connect to multiple MCP servers and manages client permissions.Client: An intermediary within the Host that manages the connection to a single MCP server, maintaining a one-to-one link. "The Client acts as an intermediary within the Host, responsible for managing the connection to a single MCP server." (Core Concepts) It handles communication lifecycle and maintains stateful sessions.Server: An external program that implements MCP and provides capabilities (tools, data, prompts) for a specific domain (e.g., databases, cloud services). "The Server is a program, typically external to the AI model itself, that implements the MCP standard and provides a specific set of capabilities." (Core Concepts) Anthropic and the community have released servers for Google Drive, Slack, GitHub, Postgres, SQLite, and web browsing.This architecture is likened to a "USB port" for AI. "This client-server architecture, often likened to a 'USB port' for AI applications, provides a standardized way for AI assistants to 'plug into' any data source or service without requiring custom code for each connection." (Core Concepts, citing source 3)3. MCP vs. REST APIs for AI Agents:Limitations of REST APIs: Require significant manual effort, lack standardized context management, often stateless, static API definitions. "Integrating AI agents with external services via REST APIs often requires significant manual effort and lacks a standardized way to manage the evolving context of agent interactions." (MCP vs. REST APIs for AI Agents)Advantages of MCP:Standardized Communication: Based on JSON-RPC, simplifying integration.Dynamic Tool Discovery: AI can query servers to understand available tools. "AI models equipped with an MCP client can query connected servers to understand the tools and resources they offer." (MCP vs. REST APIs for AI Agents)Two-Way Real-Time Interaction: Supports persistent connections for context updates.Superior Approach Scenarios: Complex workflows with multiple tools, real-time data integration, frequently changing toolsets, intelligent assistants, automated coding tools, dynamic data analytics.4. Enhancing AI Agent Effectiveness:Improved Contextual Awareness and Management: MCP allows agents to access and retain relevant context from multiple sources, overcoming context window limitations. "One of the most significant ways in which the Model Context Protocol enhances the effectiveness of AI agents is by enabling improved contextual awareness and management." (Enhancing AI Agent Effectiveness)The ability to connect to multiple servers simultaneously supports complex workflows.The "Resources" primitive provides just-in-time, modular context, leading to more efficient processing and accurate responses.Facilitating Seamless Integration: MCP eliminates the need for custom code for each new data source or tool. "By providing a standardized interface, MCP eliminates the need for developers to write custom code for each new data source or tool that an AI agent needs to interact with." (Enhancing AI Agent Effectiveness)Pre-built servers for popular systems (Google Drive, Slack, GitHub, databases) streamline integration.Supporting Advanced Reasoning and Decision-Making: The "Tools" primitive allows agents to invoke functions and access real-time data.The "Sampling" primitive enables complex, multi-step reasoning processes (with recommended human approval).Real-World Examples:Corporate chatbots querying multiple internal systems.AI-powered coding assistants (Sourcegraph Cody, Zed Editor) accessing codebases.Anthropic's Claude Desktop accessing local files. "By integrating MCP, Claude can securely access local files, applications, and services on the user's computer." (Enhancing AI Agent Effectiveness)AI2SQL generating SQL from natural language.Apify allowing AI agents to access Apify Actors for automation.5. Driving Adoption for AI Tool Providers:Standardized Integration: Reduces the complexity and costs of developing and maintaining multiple custom integrations. "By providing a single, open standard for connecting AI models with tools, MCP reduces the need for tool providers to develop and maintain multiple custom integrations tailored to different AI platforms." (Driving Adoption for AI Tool Providers)Increased Interoperability: Tools can work with any MCP-compatible AI model, broadening the potential user base and reducing vendor lock-in. "Tools built using the MCP standard can seamlessly work with any AI model that has implemented an MCP client, regardless of the AI provider (e.g., Anthropic, OpenAI) or whether it's an open-source model." (Driving Adoption for AI Tool Providers)Opportunities for Innovation and Specialization: Enables developers to create specialized servers that can be accessed by any MCP client, fostering a division of labor.Benefits for Scalability and Future-Proofing: Ensures integrations remain compatible with future AI models adhering to the standard.6. Real-World Use Cases and Examples of MCP Implementation (Detailed):Coding Assistants: Sourcegraph Cody and Zed Editor.Enterprise Integrations: Block and Apollo. "Companies like Block and Apollo have adopted MCP to securely connect their AI systems with internal data repositories and customer relationship management (CRM) systems." (Real-World Use Cases and Examples of MCP Implementation)Desktop AI Applications: Anthropic's Claude Desktop.Data Querying Tools: AI2SQL.Automation Platforms: Apify.Community-Built Servers: Numerous servers on platforms like Smithery.ai and mcp-get.com for databases, cloud services, etc.7. Future Implications and the Evolving AI Ecosystem:Fostering Interoperability and Standardization: MCP has the potential to become a universal standard for AI integration. "By establishing a universal standard for AI integration, MCP could become the equivalent of HTTP for the web or USB-C for device connectivity in the AI world." (Future Implications and the Evolving AI Ecosystem)Could decouple AI model choice from underlying integrations.Potential Impact on AI R&D and Deployment: May shift focus towards effective utilization of external information over solely increasing model size. Could lead to more modular AI system designs.Addressing Potential Challenges: Requires buy-in from AI providers and tool developers. Security is paramount. Ensuring user trust and human oversight are crucial. "Security is another paramount concern. Allowing AI agents to access and interact with external systems, especially sensitive enterprise data, necessitates robust security measures to prevent unauthorized access or data leaks." (Future Implications and the Evolving AI Ecosystem)Conclusion:MCP offers a promising path towards a more interconnected, context-aware, and effective AI ecosystem. Its standardized framework addresses critical integration challenges, enhances AI agent capabilities, and provides new opportunities for tool providers and the broader AI community. While adoption challenges exist, the potential transformative impact of MCP on the future of AI is significant.

    Zulq Malik: The future of construction coordination with SMRT-E

    Play Episode Listen Later Feb 21, 2025 22:11


    Check out SmartBuild here: https://smrtbld.com/Check out SMRT-E here: https://smrte.ai  

    David Hernandez: Planning and Project Management Software from Elecosoft

    Play Episode Listen Later Jan 28, 2025 22:42


    Check out Elecosoft here:  https://elecosoft.com/us/solutions/Follow David here.

    Eshan Jayamanne: AI Supply Chain Management at Krane

    Play Episode Listen Later Jan 23, 2025 24:59


    Check out Krane here: https://krane.tech/Follow Eshan here

    Eldar Sadikov: AI For Construction Procurement By Field Materials

    Play Episode Listen Later Jan 20, 2025 23:40


    Check out Field Materials here: https://www.fieldmaterials.com/Follow Eldar here

    Hammad Chaudhry: 2024 - The Year in Construction Technology

    Play Episode Listen Later Dec 16, 2024 27:54


    Elizaveta Taylor: Upgraded Construction Accounting at Beyond Books Solutions

    Play Episode Listen Later Nov 19, 2024 27:29


    Follow Elizaveta hereCheck out Beyond Books here: https://beyondbookssolutions.com/Check out Elizaveta's amazing videos: https://www.youtube.com/@BeyondBooksSolutions

    Daniel Hewson: Construction Data & AI at Elecosoft

    Play Episode Listen Later Nov 12, 2024 30:27


    Check out Elecosoft here: https://elecosoft.com/us/Follow Daniel here

    Nitin Bhandari: Visual Construction Scheduling at Planera

    Play Episode Listen Later Nov 5, 2024 24:11


    Follow Nitin hereCheck out Planera here: https://www.planera.io/

    Damion Lupo: Revolutionizing Construction Framing at FrameTec

    Play Episode Listen Later Oct 31, 2024 30:29


    Check out FrameTec: https://www.frametec.com/

    Sadanand Sahasrabudhe: Intelligent Construction Procurement at ConstructivIQ

    Play Episode Listen Later Oct 29, 2024 27:19


    Follow Sadanand hereCheck out ConstructivIQ here: https://constructiviq.com/ 

    Michael Pink Advanced Construction Schedule Controls at SmartPM

    Play Episode Listen Later Oct 22, 2024 29:13


    Follow Michael hereCheck out SmartPM here: https://smartpm.com/email Michael at mpink@smartpm.com

    Bill Mandara: Pushing Design Boundaries at Mancini Duffy

    Play Episode Listen Later Oct 8, 2024 23:37


    Check out Mancini Duffy on Linkedin hereFollow Bill Mandara hereCheck out Mancini Duffy's website: https://manciniduffy.com/

    Bryan Kerr:Launching an excess soil marketplace named 'Phil'

    Play Episode Listen Later Oct 1, 2024 27:28


    Check out Phil here: https://getphil.app/Follow Bryan here: https://www.linkedin.com/in/bryankerr/ 

    Tanner Dieterich: A Cloud Platform for The Real Estate Lifecycle at Built

    Play Episode Listen Later Sep 17, 2024 26:45


    Lucas Turner Owens: Investing Sustainably at Building Ventures

    Play Episode Listen Later Sep 12, 2024 24:26


    Roger Krulak: Shaping The Future of Urban Development at FullStack Modular

    Play Episode Listen Later Sep 10, 2024 26:03


    Follow Roger hereCheck out FullStack Modular here: https://www.fullstackmodular.com/

    Romey Oulton: Human-Centered ConTech Recruitment at LMRE

    Play Episode Listen Later Aug 20, 2024 27:43


    Follow Romey hereCheck out LMRE here: https://www.lmre.tech/lmre-north-america/

    JJ Levenske: Construction Group Therapy

    Play Episode Listen Later Jul 25, 2024 10:16


    Sign up for Construction Group Therapy here: https://www.linkedin.com/events/constructiongrouptherapy7219180364928274432/Check out Redteam software here: https://redteam.com/Check out The Link here: https://www.thelink.ai 

    Burcin Kaplanoglu: Innovating In The Age of AI at Oracle Innovation Labs

    Play Episode Listen Later Jun 20, 2024 28:15


    Follow Burcin hereCheck out the Oracle Innovation Lab here: https://www.oracle.com/industries/innovation-lab/

    Michal Porter: Innovating Sustainable Shelter Technologies at DuPont

    Play Episode Listen Later Jun 13, 2024 29:19


    Check out Dupont Building Solutions here: https://www.dupont.com/building.htmlFollow Michal Porter here: https://www.linkedin.com/in/michal-porter-56175513a/ICF study mentioned in the podcast is hereUN Global Status Report for Buildings and Construction is here

    Sarah Liu: Investing in a Future Proof Built World at Fifth Wall

    Play Episode Listen Later Jun 4, 2024 23:49


    Jeremy Suard: Solving The Underground at Exodigo

    Play Episode Listen Later May 30, 2024 19:56


    Jeffrey Rissman: The Road to a Zero-Carbon Industrial Nation

    Play Episode Listen Later May 21, 2024 25:42


    Follow Jeff hereGet the book at a 20% discount here: https://zerocarbonindustry.com/

    Tony Nicolaidis-Safety and Security through WiFi Sensing

    Play Episode Listen Later May 7, 2024 20:09


    Check out Origin here: https://www.originwirelessai.com/Follow Tony here

    Michael Wright: Creating Construction Software for Total Project Control at RedTeam

    Play Episode Listen Later Apr 30, 2024 23:02


    Learn more about RedTeam here: https://redteam.com/Follow Michael Wright here

    David Deloury: Software to Build Safety Culture at Safeto

    Play Episode Listen Later Apr 25, 2024 24:20


    Check out Safeto here: https://www.safe-to-work.com/Follow David here: https://www.linkedin.com/in/david-deloury-0a122b96/

    Innovating Through Building Codes at ICC

    Play Episode Listen Later Apr 23, 2024 22:30


    Follow Ryan hereCheck out ICC here: https://iccsafe.com/

    Steven Solloway: How Construction Field Teams Find It Fast with SpecGPT

    Play Episode Listen Later Apr 15, 2024 13:01


    Blima Ehrentreu: Designing with Purpose at The Designer's Group

    Play Episode Listen Later Apr 11, 2024 26:15


    Follow Blima hereCheck out The Designer's Group here: https://www.thedesignersgroup.com/

    Jeffrey Potter: Exploring the Future of Construction Specifications

    Play Episode Listen Later Apr 9, 2024 23:09


    Dustin Devan Building a New Paradigm for Preconstruction at Ediphi

    Play Episode Listen Later Apr 4, 2024 21:49


    Follow Dustin hereCheck out Ediphi here: https://www.ediphi.com/

    The Link: Find It Fast with SpecGPT

    Play Episode Listen Later Apr 2, 2024 14:24


    Get SpecGPT here: https://specgpt.aiCheck out The Link hereFollow Hugh here

    Geoff Smith Architecting Construction's Future at EllisDon

    Play Episode Listen Later Mar 28, 2024 26:25


    Follow Geoff Smith hereCheck out EllisDon's Digital team here: https://www.ellisdon.com/actions/digitize

    Marty Cornish: AI powered Construction Takeoff at Workpack

    Play Episode Listen Later Mar 21, 2024 23:31


    Follow Marty hereCheck out Workpack here: https://www.workpack.ai/

    Chris Hale: Cybersecurity for Startups and Contractors at Technology Response Team

    Play Episode Listen Later Mar 19, 2024 24:32


    Follow Chris hereCheck out Technology Response Team here: https://www.technologyresponse.com/

    Ezequiel Machabanski: Building Data Infrastructure at EllisDon

    Play Episode Listen Later Mar 14, 2024 23:51


    Follow Eze hereCheck out EllisDon's Insights and Analytics here: https://www.ellisdon.com/actions/advise/insights-and-analytics

    Jonathan Porter-Whistman: Accurately Predicting Talent Performance at Perception Predict

    Play Episode Listen Later Mar 12, 2024 24:13


    Follow Jonathan hereCheck out Perception Predict here: https://www.perceptionpredict.ai/

    Alastair Blenkin: Digital Transformation of Buyout/Procurement at ProcurePro

    Play Episode Listen Later Mar 7, 2024 22:44


    Check out ProcurePro here: https://procurepro.co/Follow Alastair here: https://www.linkedin.com/in/alastairblenkin/

    Samantha Erlich: Creating the Foundations of Building Digital at EllisDon

    Play Episode Listen Later Mar 5, 2024 25:29


    Follow Samantha hereCheck out EllisDon's Digital Data & Engineering Group: https://www.ellisdon.com/actions/digitize

    Keith Robinson How to Write Consumable Specifications

    Play Episode Listen Later Feb 28, 2024 25:26


    Claim Constructed Futures

    In order to claim this podcast we'll send an email to with a verification link. Simply click the link and you will be able to edit tags, request a refresh, and other features to take control of your podcast page!

    Claim Cancel