Ian McClanan

🆕 The Full Story of Notion AI latent.space/p/notion We're so excited to chat with @simonlast and @sarahmsachs about Notion's "Token Town" - the crack team of AI Engineers and Model Behavior Engineers entrusted with building AI for Silicon Valley's most beloved knowledge work collaboration platform - and their latest launch of Custom Agents! We talked: • The full history of the 5 major rebuilds of Notion AI — and the key lessons from each • How to eval agent *usefulness* not just correctness • MCP vs CLI pros and cons • What "work" looks like when agents are coworkers — why they build for the "top of the class" rather than dumb down AI for everyone • Simon's take on the ideal "software factory" of the future and so much more! Timestamps: 00:00:00 Introduction and launching Notion Custom Agents 00:01:17 Why Notion rebuilt agents four or five times 00:03:35 Building for where models are going, not just where they are 00:05:32 The Agent Lab thesis, wrappers, and product intuition 00:08:07 User journeys, leadership, and low-ego AI teams 00:13:16 The Simon Vortex, hackathons, and bringing security in early 00:16:39 Team structure, demos over memos, and building for agents 00:20:25 Evals, Notion’s Last Exam, and the Model Behavior Engineer role 00:27:37 Evals as an agent harness and the changing role of software engineers 00:30:42 The software factory: specs, verification, and agent workflows 00:32:18 Live demo: a custom agent for coworking space applications 00:35:08 Composing agents, manager agents, and memory as pages 00:38:15 Notion Mail, Gmail, native integrations, and tools 00:39:43 MCP vs CLI and the cost of capability 00:44:13 When Notion uses MCP vs building its own integrations 00:47:43 The history of Notion’s agent harness rebuilds 00:55:35 Power users, public tools, and the setup agent 00:58:01 Self-fixing agents, permissions, and “flippy” 01:01:13 Pricing, credits, and choosing the right model automatically 01:09:01 Why Notion isn’t training its own frontier model 01:14:07 Retrieval, ranking, and search built for agents 01:17:27 Meeting Notes as data capture and workflow automation 01:21:18 Wearables, hardware, and Notion as the system of record 01:23:45 Outro

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at @NotionHQ. And you can build one.

Recently, @ivanhzhao put words to something we’ve long believed: "The most meaningful things were never built alone. It’s always groups of people, building and believing until something clicks." So much of that work happens when people are together in offices, where ideas are discussed and tugged at and strengthened when people gather around them. Space influences how people “think together.” Today, we’re excited to launch a new video series about the stories behind the physical spaces the best companies inhabit, and what those spaces reveal about how great work gets done. It feels especially fitting to begin with @NotionHQ. We began our partnership with the company long before they had an office, or even a product. Join @akothari as he gives us a tour of Notion’s SF office

Tomorrow we’re breaking down how companies actually become AI-native. Using the AI Transformation Model + a real case study from Ramp. Ben Levick (Head of AI @ Ramp) will talk through how they did it from the inside. If you’re figuring this out right now, you should join. info.notion.so/webinar/webina…