How to Make AI Actually Do Things | Alex Hancock, Block, Goose, MCP Steering Committee

Aug 23, 2025

In this discussion, Alex Hancock, a Senior Software Engineer at Block and key player in the development of Goose, shares insights into the emerging Model Context Protocol (MCP). Exploring how MCP transforms AI from mere models into functional agents, he emphasizes the importance of open governance and context management. They dive into challenges in API development and the necessity for intuitive AI interfaces. Alex also reveals his expectations for AGI's incremental arrival and how a long-term mindset shapes his contributions to AI infrastructure.

Ask episode

AI Snips

Chapters

Books

Transcript

Episode notes

INSIGHT

MCP Lets Models Act In The World

MCP removes the "brain in a jar" problem by connecting models to nearby data and tools.
It gives models "arms and legs" so they can read resources and perform actions in other systems.

ANECDOTE

Block Adopted MCP Early

Block adopted MCP early because it matched Goose's needs for flexible tools and resource access.
Alex found the spec fit their agent work and was pleased by its rapid adoption.

INSIGHT

Steering Committee Is Formalizing Governance

The MCP steering committee began as contributors and implementers coordinating via GitHub.
They recently published a governance and stewardship framework to open participation.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Right now, the biggest leap for AI isn’t a bigger model – it’s giving models and agents a way to act.

In this episode of Inference, I sit down with Alex Hancock – Senior Software Engineer at Block, core contributor to Goose (the open-source, multi-purpose AI agent), and a member of the Model Context Protocol (MCP) Steering Committee – to talk about the infrastructure that’s quietly powering the next wave of AI.

*We cover:*

– What MCP is – and why it’s exploding in adoption

– How it turns models from “brains in jars” into agents with arms and legs

– The MCP Steering Committee’s push for openness and real governance

– Why SDK parity, registry design, and OAuth 2.1 are make-or-break for developers

– How MCP and A2A fit together – and where they might compete

– Context discovery, context management, and why they’re the hardest problems in agentic AI

– The lessons from Goose on staying model-agnostic in a fast-moving ecosystem

– What this shift means for software development – and for the humans in the loop

Alex also shares his view on the next year of protocol development, why he thinks AGI will arrive incrementally, and how a runner’s mindset shapes his approach to building tools that last.

If you’re building agents, connecting models to the world, or just trying to understand the emerging “protocol layer” of AI, this conversation will give you a front-row seat.

Let’s find out how we’re teaching AI to act – and what’s still missing.

*Did you like the episode? You know the drill:*

📌 Subscribe for more conversations with the builders shaping real-world AI.

💬 Leave a comment if this resonated.

👍 Like it if you liked it.

🫶 Thank you for watching and sharing!

*Guest:*

Alex Hancock, Senior Software Engineer at Block, Goose Maintainer & MCP Steering Committee Member

https://www.linkedin.com/in/alexjhancock/

https://x.com/alexjhancock

https://github.com/block/goose

MCP https://github.com/modelcontextprotocol

Building to Last: A New Governance Model for MCP https://blog.modelcontextprotocol.io/posts/2025-07-31-governance-for-mcp/

*📰 Want the transcript and edited version?*

Subscribe to Turing Post: https://www.turingpost.com/subscribe

Chapters *coming*

Turing Post is a newsletter about AI's past, present, and future. Publisher Ksenia Se explores how intelligent systems are built – and how they’re changing how we think, work, and live.

*Follow us:*

Ksenia and Turing Post:

https://x.com/TheTuringPost

https://www.linkedin.com/in/ksenia-se

https://huggingface.co/Kseniase