https://agentsinuse.comPublished agent use cases and field guides. Use case examples and drafts excluded; video examples explicitly labeled.https://agentsinuse.com/use-cases/claude-cloudflare-waf-rule/https://agentsinuse.com/use-cases/claude-cloudflare-waf-rule/Willison 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/claude-local-video-compressor/https://agentsinuse.com/use-cases/claude-local-video-compressor/Willison 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/claude-gif-optimizer/https://agentsinuse.com/use-cases/claude-gif-optimizer/Willison 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/claude-moebius-browser-port/https://agentsinuse.com/use-cases/claude-moebius-browser-port/Willison 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/claude-record-canvas-video/https://agentsinuse.com/use-cases/claude-record-canvas-video/Willison 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/claudius-shop-browser-research/https://agentsinuse.com/use-cases/claudius-shop-browser-research/In 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/claudius-office-shop/https://agentsinuse.com/use-cases/claudius-office-shop/Anthropic 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/codex-datasette-blog/https://agentsinuse.com/use-cases/codex-datasette-blog/Willison 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/codex-datasette-rate-limit/https://agentsinuse.com/use-cases/codex-datasette-rate-limit/When 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/codex-blog-markdown-fix/https://agentsinuse.com/use-cases/codex-blog-markdown-fix/Simon 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/codex-justhtml-port/https://agentsinuse.com/use-cases/codex-justhtml-port/Willison 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/cursor-hybrid-search/https://agentsinuse.com/use-cases/cursor-hybrid-search/Dodds 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/cursor-one-shot-audio-sandbox/https://agentsinuse.com/use-cases/cursor-one-shot-audio-sandbox/Dodds 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/deep-research-orchestrions/https://agentsinuse.com/use-cases/deep-research-orchestrions/Willison 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/robin-retinal-research/https://agentsinuse.com/use-cases/robin-retinal-research/FutureHouse 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/videos/video-terminal-sharing/https://agentsinuse.com/videos/video-terminal-sharing/Willison 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. Key takeaways: Reference existing tools to make the requested behavior concrete. Review terminal output before creating a public sharing link.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/videos/video-datasette-plugin-upgrade/https://agentsinuse.com/videos/video-datasette-plugin-upgrade/Willison 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. Key takeaways: A passing test can miss a real page error; reproduce the behavior first. Give the agent a failing runner and the precise migration guide.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/use-cases/wikicrow-gene-drafts/https://agentsinuse.com/use-cases/wikicrow-gene-drafts/FutureHouse 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.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/blog/choose-first-sourced-use-case/https://agentsinuse.com/blog/choose-first-sourced-use-case/Use a visible defect, an independent check and a bounded workspace to choose a first agent task. A practical guide grounded in sourced deployments.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/blog/sourced-use-cases-october-14/https://agentsinuse.com/blog/sourced-use-cases-october-14/An editorial review of the October 14 collection: tested patches, browser work, research drafts and shopkeeping failures, with primary sources and practical limits.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/blog/write-agent-approval-checkpoints/https://agentsinuse.com/blog/write-agent-approval-checkpoints/Define the action, evidence, approver and expiry for agent permissions. Includes concrete checkpoints for WAF edits, supplier quotes and code publication.Wed, 14 Oct 2026 00:00:00 GMThttps://agentsinuse.com/videos/example-video-research-checkpoint/https://agentsinuse.com/videos/example-video-research-checkpoint/EXAMPLE ONLY. No recording attached. An illustrative video entry showing how an agent workflow could be reviewed, with a deliberate human checkpoint. Key takeaways: Set a bounded goal before handing work to an agent. Review evidence and approve consequential actions at a human checkpoint.Tue, 13 Oct 2026 00:00:00 GMThttps://agentsinuse.com/videos/example-video-workflow-review/https://agentsinuse.com/videos/example-video-workflow-review/EXAMPLE ONLY. No recording attached. An illustrative video entry showing how an agent workflow could be reviewed, with a deliberate human checkpoint. Key takeaways: Set a bounded goal before handing work to an agent. Review evidence and approve consequential actions at a human checkpoint.Tue, 13 Oct 2026 00:00:00 GMT