Agents In Use13 use cases
simonwillison.netWillison wanted to optimize a phone recording before publishing it. He used Claude Code for web to build a browser tool around FFmpeg compiled to WebAssembly, with multiple output presets.
simonwillison.netWillison asked Claude Code for web to compile Gifsicle to WebAssembly and build a preview interface. The agent used Rodney to exercise the page and fix UI bugs during implementation.
simonwillison.netWillison delegated a Moebius model port to Claude Code using local repositories and a research note. He tested the browser UI and returned errors while the agent iterated on ONNX and WebGPU support.
gist.github.comWillison published the Codex session used to build the Datasette project blog. The agent inspected the existing site, moved conflicting database routes and implemented blog behavior with local checks.
simonwillison.netSimon Willison gave Codex a specific defect in his Django blog: social preview descriptions exposed raw Markdown. Codex changed templates and added a passing test in a configured PostgreSQL environment.
simonwillison.netWillison supplied an existing parser and an independent compatibility suite, reviewed an API plan, then let Codex implement a JavaScript port through repeated tests and commits.
kentcdodds.comDodds used Cursor with GPT-5.4 to add lexical retrieval to his semantic search. Production blocking exposed an architectural flaw, so later agent work moved search into a unified Worker.
kentcdodds.comDodds delegated an audio pipeline migration to Cursor. He rejected an initial design that preserved a separate service and used another agent run to make the sandbox part of the existing queue Worker.
simonwillison.netWillison recorded a real build with Claude Code for web, turning pasted terminal output into shareable HTML. The companion article explains the repository references and the workflow behind the recording.
simonwillison.netWillison recorded upgrading datasette-checkbox for a changed permissions API. He first repaired a test that missed a real page failure, then gave Codex the failing runner and upgrade documentation.
An illustrative video entry showing how an agent workflow could be reviewed, with a deliberate human checkpoint.
Inspect proposed dependency updates, review upstream changes, and test compatibility in a disposable environment.
Inspect a repository, reproduce a reported bug, and prepare a tested patch for review.