Agent Field Notes

Latest briefing,

Publishing with agents: what Google, AI search and agent-ready websites mean for one-person businesses

Search traffic is shrinking, Google is still pruning mass-produced pages, and websites are starting to be graded on whether AI agents can use them. Each shift rewards small sites that publish original data.

Read the briefing

New and notable tools

All 5 tools
  • Anubis

    Local models

    Mac app for testing and benchmarking local models on Apple Silicon, with live power, thermal and memory readings during inference.

  • asiai

    Local models

    Command-line tool that compares local AI inference engines side by side on an Apple Silicon Mac, with community benchmarks.

  • Free scanner from Cloudflare that scores any website on how ready it is for AI agents, with fix-it prompts you can hand to a coding agent.

  • Checks the quality of an MCP server — tool naming, descriptions, metadata for directories — and suggests concrete fixes.

  • MetriLLM

    Local models

    One-command benchmark for local models that scores speed, quality and hardware fit, with a shareable result and public leaderboard.

Built here

All projects

Projects appear here once they are published as public repositories on GitHub.