How do you deploy AI agents to 12,000 employees in just 8 weeks? How do you do it safely? Angie Jones, VP of Engineering for AI Tools and Enablement at Block, joins the show to share exactly how her team pulled it off.Block (the company behind Square and Cash App) became an early adopter of Model Context Protocol (MCP) and built Goose, their open-source AI agent that's now a reference implementation for the Agentic AI Foundation. Angie shares the challenges they faced, the security guardrails they built, and why letting employees choose their own models was critical to adoption.We also dive into vibe coding (including Angie's experience watching Jack Dorsey vibe code a feature in 2 hours), how non-engineers are building their own tools, and what MCP unlocks when you connect multiple systems together.Chapters:00:00 Introduction02:02 How Block deployed AI agents to 12,000 employees05:04 Challenges with MCP adoption and security at scale07:10 Why Block supports multiple AI models (Claude, GPT, Gemini)08:40 Open source models and local LLM usage09:58 Measuring velocity gains across the organization10:49 Vibe coding: Benefits, risks & Jack Dorsey's 2-hour feature build13:46 Block's contributions to the MCP protocol14:38 MCP in action: Incident management + GitHub workflow demo15:52 Addressing MCP criticism and security concerns18:41 The Agentic AI Foundation announcement (Block, Anthropic, OpenAI, Google, Microsoft)21:46 AI democratization: Non-engineers building MCP servers24:11 How to get started with MCP and prompting tips25:42 Security guardrails for enterprise AI deployment29:25 Tool annotations and human-in-the-loop controls30:22 OAuth and authentication in Goose32:11 Use cases: Engineering, data analysis, fraud detection35:22 Goose in Slack: Bug detection and PR creation in 5 minutes38:05 Goose vs Claude Code: Open source, model-agnostic philosophy38:17 Live Demo: Council of Minds MCP server (9-persona debate)45:52 What's next for Goose: IDE support, ACP, and the $100K contributor grant47:57 Where to get started with GooseConnect with Angie on LinkedIn: https://www.linkedin.com/in/angiejones/Angie's Website: https://angiejones.tech/Follow Angie on X: https://x.com/techgirl1908Goose GitHub: https://github.com/block/gooseConnect with Conor on LinkedIn: https://www.linkedin.com/in/conorbronsdon/Follow Conor on X: https://x.com/conorbronsdonModular: https://www.modular.com/Presented By: Galileo AIDownload Galileo's Mastering Multi-Agent Systems for free here: https://galileo.ai/mastering-multi-agent-systemsTopics Covered:- How Block deployed Goose to all 12,000 employees- Building enterprise security guardrails for AI agents- Model Context Protocol (MCP) deep dive- Vibe coding benefits and risks- The Agentic AI Foundation (Block, Anthropic, OpenAI, Google, Microsoft, AWS)- MCP sampling and the Council of Minds demo- OAuth authentication for MCP servers- Goose vs Claude Code and other AI coding tools- Non-engineers building AI tools- Fraud detection with AI agents- Goose in Slack for real-time bug fixing

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Transcript

Related