I've been testing Muse lately. A very capable, utility-minded personal agent in your pocket. Strong browser use. The spin on feed is interesting (still getting used to it.) A great entrance to the agent space!

We just shipped something a bit different: Notion Knowledge Board Our goal is to measure how well different models 'get the job done' on real tasks. We picked 15 models that passed our internal evals, split real production traffic across them, and used an ensemble of judges from Anthropic, OpenAI, and Google to score the results. Quality came out close across all models: 94-98%, open source included. Cost varies a lot: $0.02 to $0.87 per task. For most everyday work, cheaper models are now good enough. AI bills are climbing--and picking the right model is an easy way to spend less without losing much.

There’s a gap between how models benchmark and how they FEEL in real-world knowledge work. Our research team wanted to study the latter, so they created the Notion Knowledge Board: live, anonymized traffic scored by an ensemble judge built with researchers at Anthropic and OpenAI. TLDR: — Real work is messier than benchmarks — Open and closed models both have their place — Fast models can also be capable

Today we're sharing the Notion Knowledge Board. We get to observe a wide range of real-world AI tasks at @NotionHQ: meeting follow-ups, support tickets, sales pipeline updates, market research, all the good stuff. Knowledge board is a live, ongoing eval of how models handle real knowledge work measured on live anonymized traffic and scored by an ensemble judge we built in collaboration with researchers at Anthropic and OpenAI. The takeaway is the tradeoffs: cost per task variance is high, and some of the fastest models are also very capable. The right model genuinely depends on your work. We will update as new models ship:

Most model evaluations rely on fixed, curated tasks. They’re useful, but they don’t show how models perform on the messy, varied work people actually give them. That’s the motivation behind @NotionHQ’s Knowledge Board. It uses a small, random, anonymized sample of live traffic, split evenly across models, to measure whether real world tasks are successfully resolved, as well as the time and cost required. Rather than offering a typical leaderboard, the project aims to answer a more practical question: Which model offers the right tradeoff for the work you’re trying to do?

To my friends building with the @NotionDevs platform. Today we shipped some tools just for you in your Notion workspace. You now have a Developer settings pane where you can toggle on the developer toolbar UI and the new embedded developer tools.

Developers: we’re opening up an early alpha for custom blocks. It’s a new Notion primitive for building interactive blocks that can read your workspaces and databases. Very early, very experimental, and we’d love to learn from what you build with it! 🧵 to be one of our first alpha testers

📁 Notion ┃ ┣ 📁 System of Record ┃ ┣ 📁Databases ┃ ┣ 📁Meeting Notes ┃ ┣ 📁Version Control ┃ ┣ 📁Wiki ┃ ┣ 📁Projects ┃ ┣ 📁Docs ┃ ┣ 📁Tasks ┃ ┣ 📁Forms ┃ ┗ 📁Knowledge base ┃ ┣ 📁 Notion AI ┃ ┣ 📁Custom Agents ┃ ┣ 📁External Agents ┃ ┣ 📁Enterprise Search ┃ ┣ 📁AI Meeting Notes ┃ ┣ 📁Deep Research ┃ ┣ 📁Autofill ┃ ┣ 📁AI Connectors ┃ ┗ 📁Mobile Agents ┃ ┣ 📁 Developer Platform ┃ ┣ 📁MCP ┃ ┣ 📁Workers ┃ ┣ 📁API ┃ ┣ 📁ntn CLI ┃ ┣ 📁Webhooks ┃ ┣ 📁Syncs ┃ ┣ 📁Agent tools ┃ ┣ 📁Developer Portal ┃ ┗ 📁External Agents API ┃ ┣ 📁 Connected Workspace ┃ ┣ 📁Slack ┃ ┣ 📁Calendar ┃ ┣ 📁Mail ┃ ┣ 📁GitHub ┃ ┣ 📁Jira ┃ ┣ 📁Asana ┃ ┣ 📁Figma ┃ ┣ 📁Zapier ┃ ┣ 📁Salesforce ┃ ┗ 📁Google Drive ┃ ┣ 📁 Business Workflows ┃ ┣ 📁CRM ┃ ┣ 📁Roadmaps ┃ ┣ 📁Launch plans ┃ ┣ 📁Editorial calendars ┃ ┣ 📁Customer research ┃ ┣ 📁Team updates ┃ ┣ 📁Onboarding ┃ ┣ 📁Approvals ┃ ┗ 📁Reporting ┃ ┣ 📁 Personal Productivity ┃ ┣ 📁Personal OS ┃ ┣ 📁Notes ┃ ┣ 📁Tasks ┃ ┣ 📁Goals ┃ ┣ 📁Reading lists ┃ ┣ 📁Travel planning ┃ ┣ 📁Habit tracking ┃ ┣ 📁Side projects ┃ ┗ 📁Life admin