https://agentsinuse.com/2026-10-14T00:00:00ZAgents In Use editorialhttps://agentsinuse.com/use-cases/claude-cloudflare-waf-rule/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/claude-local-video-compressor/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/claude-gif-optimizer/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/claude-moebius-browser-port/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/claude-record-canvas-video/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/claudius-shop-browser-research/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/claudius-office-shop/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/codex-datasette-blog/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/codex-datasette-rate-limit/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/codex-blog-markdown-fix/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/codex-justhtml-port/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/cursor-hybrid-search/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/cursor-one-shot-audio-sandbox/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/deep-research-orchestrions/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/robin-retinal-research/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/videos/video-terminal-sharing/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/videos/video-datasette-plugin-upgrade/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/use-cases/wikicrow-gene-drafts/2026-10-14T00:00:00Z

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.

https://agentsinuse.com/blog/choose-first-sourced-use-case/2026-10-14T00:00:00Z

Use a visible defect, an independent check and a bounded workspace to choose a first agent task. A practical guide grounded in sourced deployments.

https://agentsinuse.com/blog/sourced-use-cases-october-14/2026-10-14T00:00:00Z

An editorial review of the October 14 collection: tested patches, browser work, research drafts and shopkeeping failures, with primary sources and practical limits.

https://agentsinuse.com/blog/write-agent-approval-checkpoints/2026-10-14T00:00:00Z

Define the action, evidence, approver and expiry for agent permissions. Includes concrete checkpoints for WAF edits, supplier quotes and code publication.

https://agentsinuse.com/videos/example-video-research-checkpoint/2026-10-13T00:00:00Z

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.

https://agentsinuse.com/videos/example-video-workflow-review/2026-10-13T00:00:00Z

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.