{"podcast":{"title":"Latent Space: The AI Engineer Podcast","slug":"latent-space-ai-engineer","podcast_index_feed_id":6058902,"rss_url":"https://api.substack.com/feed/podcast/1084089.rss","website_url":"https://www.latent.space/podcast","image_url":"https://substackcdn.com/feed/podcast/1084089/ca7468da5614a246d2906ee8926f6de7.jpg","author":"Latent.Space","episode_count":204,"summary":"The AI Engineer newsletter + Top technical AI podcast. How leading labs build Agents, Models, Infra, & AI for Science. See https://latent.space/about for highlights from Greg Brockman, Andrej Karpathy, George Hotz, Simon Willison, Soumith Chintala et al!","last_synced_at":null,"page_url":"https://stenobird.com/podcast/latent-space-ai-engineer"},"episode":{"title":"Notion’s Token Town: 5 Rebuilds, 100+ Tools, MCP vs CLIs and the Software Factory Future — Simon Last & Sarah Sachs of Notion","slug":"notion-s-token-town-5-rebuilds-100-tools-mcp-vs-clis-and-the-software-factory-future-simon-last-sarah-sachs-of-notion","published_at":"2026-04-15T00:31:14+00:00","page_url":"https://stenobird.com/podcast/latent-space-ai-engineer/notion-s-token-town-5-rebuilds-100-tools-mcp-vs-clis-and-the-software-factory-future-simon-last-sarah-sachs-of-notion","show_page_url":"https://stenobird.com/podcast/latent-space-ai-engineer","url":"https://www.latent.space/p/notion","audio_url":"https://api.substack.com/feed/podcast/194195821/10f31b379fbf657fd80757e3b4244e4f.mp3","summary":"Notion engineers reveal why they rebuilt their AI agent architecture five times to move beyond simple model wrapping. The discussion explores the transition from basic tool-calling to a robust 'Agent Lab' capable of complex, autonomous workflows.","meta_description":"Go inside Notion's AI engineering journey: from failed 2022 experiments to building a scalable, agent-native system of record using MCP and CLIs.","key_points":["Main idea: The 'Agent Lab' thesis focuses on building product systems around frontier capabilities rather than just wrapping LLMs","Failure mode: Early agent attempts failed due to lack of tool-calling standards, short context windows, and excessive complexity exposed to the model","Practical takeaway: Using MCP (Model Context Protocol) provides a superior, tightly permissioned security model compared to the murkier risks of CLIs","Engineering insight: Effective AI product development requires 'Model Behavior Engineers' to focus on high-quality evals and data-driven refinement","Future vision: The shift toward 'software factories' where agents autonomously spec, code, test, and maintain entire codebases"],"chapters":[{"start_ms":60000,"title":"The Iterative Path to Production","summary":"How Notion manages the tension between shipping stable alpha features and simultaneously developing the next generation of AI tools."},{"start_ms":410000,"title":"The Agent Lab Thesis","summary":"A deep dive into why Notion's approach to AI is about building a system for collaboration rather than just a chatbot interface."},{"start_ms":770000,"title":"High-Velocity Engineering Culture","summary":"How Notion organizes engineering teams to handle the rapid, daily shifts in direction inherent in the AI era."},{"start_ms":1460000,"title":"The Rise of Model Behavior Engineers","summary":"Discussing the evolution of specialized roles focused on evaluating model outputs and managing complex tool-calling logic."},{"start_ms":2160000,"title":"MCP vs. CLIs: The Security Frontier","summary":"Comparing the utility of the Model Context Protocol for lightweight agents against the power and risks of terminal-based environments."},{"start_ms":3555000,"title":"Agentic Pricing and Workflows","summary":"Exploring the economic and technical challenges of charging for token usage in a world of varying model capabilities."},{"start_ms":4245000,"title":"Meeting Notes as Data Capture","summary":"How Notion views meeting transcription as the foundational data layer for future autonomous agentic workflows."}],"topics":["AI Agents","Model Context Protocol","Software Engineering","Product Development","Notion AI","LLM Tool Calling","Agentic Workflows","Enterprise AI"],"duration_seconds":4637,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/latent-space-ai-engineer/episodes/notion-s-token-town-5-rebuilds-100-tools-mcp-vs-clis-and-the-software-factory-future-simon-last-sarah-sachs-of-notion/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/latent-space-ai-engineer/notion-s-token-town-5-rebuilds-100-tools-mcp-vs-clis-and-the-software-factory-future-simon-last-sarah-sachs-of-notion.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}