Skip to main content

Writing

Notes on AI, agents, web technologies, and building with LLMs

Technical articles on building with LLMs: agents and agent harnesses, MCP, evaluation, and the web technologies underneath. Worked examples with code, written for working developers.

The newsletter

Ctrl+Alt+Delegate

The three-finger salute for work you should not be doing yourself.

251 articles · Page 1 of 26

Filter by tag

  1. Your AI rollout raised the ceiling. Now raise the floor.

    A licence rollout makes your best people better and leaves everyone else where they were. 2 ways companies raise the floor, why most organisations can't use either, and a one-question test for whether yours has moved.

    AIAI adoption

  2. What happens when AI gets its own computer and stops waiting for prompts

    Close your laptop and almost every AI tool you use stops dead. Always-on bots get their own cloud computer, their own memory and their own triggers. How they're designed, and what that changes about handing work over.

    AIAgentsAgentic AI

  3. Searching English text in Spanish, and why "balompié" goes skiing

    A Spanish search finds the right English sentence, and a formal Spanish word for football finds a ski trip. What an embedding model reads, what it gives back, how to tell a real match from a guess, and what changes with a second model running locally.

    AIEmbeddingsSQLiteMultilingual

  4. EmbeddingGemma 2 in the browser: one search box for photos, sound, video and notes

    How EmbeddingGemma 2 puts text, images, audio and video into one vector space, and what it takes to run it entirely in a browser tab on WebGPU: token budgets, a 2,700-token wall, Matryoshka truncation, offline search, and why q4 doesn't load on WASM.

    AIEmbeddingsWebGPUTransformers.js

  5. How Code Mode turns MCP tools into a TypeScript API

    Code Mode gives the model a TypeScript API instead of a list of tools, then runs the program it writes in a sandbox. How the pattern works, built from scratch on MCP, QuickJS and Gemini, and where it gets fiddly.

    AIAgentic AIMCPTool Calling

  6. Most people are using AI back to front

    People hand AI the thinking and keep the searching, reading and table-filling for themselves. It should be the other way round. What to hand over, what to keep, and why knowing your subject matters more now.

    AIAI adoptionProductivity

  7. Jev, the model that can't write

    Jev is a model that cannot generate a single word of text. It picks from options you give it and returns a probability for each, dozens of questions per call, in a few hundred milliseconds. To see what that's good for I gave it a gamebook to referee: you type anything, Jev decides what you meant, whether it would work, and what it says about you.

    InteractiveAITypeSafeGeminiEngineeringGames

  8. MCP, WebMCP, A2A and ARD

    Four protocols cover almost everything an agent needs to reach: a tool, a web page, another agent, and a catalogue of what exists. MCP and WebMCP are separate specifications by different authors. ARD is four months old and indexes the other three. Here's what each one is and who's on each end of the wire.

    AIAgentsMCPA2AProtocols

  9. Musubi: a history of everything you asked

    I have thousands of conversations with AI tools scattered across four applications. Musubi reads all of them, distils them, and hands the result back to any agent over MCP, with nothing ever leaving the machine.

    AILocal-firstMCPSQLiteEngineering

  10. Stop asking the model to remember arithmetic

    Most of what is in my skill files should not be there. A skill is knowledge the model needs while it works; a check is a fact about whether the output came out right. Almost everything I had written into skill files was the second kind wearing the clothes of the first.

    InteractiveAIAgentsAgent SkillsVerification