Agents In Use32 use cases
til.simonwillison.netWillison used Claude Code to narrow a Cloudflare challenge to multi-parameter searches. When the MCP interface could not edit the relevant rules, the agent switched to the API.
Added
Claudevia Claude Code
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.
AddedClaudevia Claude Codesimonwillison.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.
AddedClaudevia Claude Codesimonwillison.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.
AddedClaudevia Claude Codesimonwillison.netWillison needed a video of an interactive canvas animation for a keynote slide. A local Claude Code session used Playwright to open the page, time clicks and produce a recording.
AddedClaudevia Claude Code
anthropic.comIn the next office-shop phase, Claudius gained browser access, CRM and better inventory context. It checked supplier prices and delivery details while human purchase approval remained mandatory.
Added
Claudiusanthropic.comAnthropic and Andon Labs let a Claude-based agent manage a real office shop. It searched for products, set prices and requested restocking, but the researchers report losses and persistent mistakes.
AddedClaudius
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.
Added
Codexsimonwillison.netWhen crawlers hammered datasette.io, Willison used Codex to build a configurable IP rate-limiting plugin. His release note includes the configuration used on the live site.
AddedCodexsimonwillison.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.
AddedCodexsimonwillison.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.
AddedCodex
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.
Added
Cursorkentcdodds.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.
AddedCursortil.simonwillison.netWillison ran o4-mini-deep-research to find surviving orchestrions and return structured location records. The model used web search and code execution; he explicitly considered the resulting list incomplete and unverified.
Added
OpenAI deep research
futurehouse.orgFutureHouse used Robin to connect literature research, experiment planning and analysis for dry age-related macular degeneration. Human researchers ran the lab work; the system proposed follow-up candidates from the results.
Added
Robinsimonwillison.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.
AddedClaudevia Claude Codesimonwillison.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.
AddedCodexfuturehouse.orgFutureHouse ran WikiCrow to draft scientific summaries of human genes using full-text papers. Its PaperQA agent searched, gathered evidence and returned to retrieval when terminology or evidence required it.
Added
WikiCrowRead merged changes, investigate user impact, and assemble a release draft with references back to the work.
Added
OpenClawDevelop a set of campaign directions, evaluate them against a brief, and prepare a coherent creative proposal.
Added UnknownInvestigate public supplier information, compare it against procurement criteria, and prepare an evidence-backed shortlist.
Added
Grok BotAn illustrative video entry showing how an agent workflow could be reviewed, with a deliberate human checkpoint.
AddedOpenClawAn illustrative video entry showing how an agent workflow could be reviewed, with a deliberate human checkpoint.
AddedOpenClawCompare recurring support questions with existing documentation and draft improvements for missing explanations.
AddedOpenClawInspect proposed dependency updates, review upstream changes, and test compatibility in a disposable environment.
AddedOpenClawReview a saved reading list, follow relevant references, and prepare a concise digest tailored to stated interests.
Added
Hermes AgentReconcile tasks and calendar commitments, identify conflicts, and draft a realistic weekly plan.
AddedHermes AgentInspect a repository, reproduce a reported bug, and prepare a tested patch for review.
AddedOpenClawExpand a story brief into a scene sequence, check continuity, and create a production-ready storyboard outline.
Added UnknownInvestigate a defined question across multiple sources and produce a brief with traceable claims.
AddedHermes AgentReview incoming messages, gather missing context, and turn requests into a prioritized queue of draft actions.
AddedHermes AgentMonitor a bounded set of public information sources and explain changes against an established baseline.
AddedGrok Bot