Article
Choose your first delegated use case from real accounts
Use a visible defect, an independent check and a bounded workspace to choose a first agent task. A practical guide grounded in sourced deployments.
AGENTS IN USE / WEEKLY
Unsent example digest. Includes illustrative use cases and unpublished drafts.
Article
Use a visible defect, an independent check and a bounded workspace to choose a first agent task. A practical guide grounded in sourced deployments.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Use case
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.
Video
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.
Video
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.
Article
An editorial review of the October 14 collection: tested patches, browser work, research drafts and shopkeeping failures, with primary sources and practical limits.
Use case
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.
Article
Define the action, evidence, approver and expiry for agent permissions. Includes concrete checkpoints for WAF edits, supplier quotes and code publication.
EXAMPLE · Use case
Read merged changes, investigate user impact, and assemble a release draft with references back to the work.
EXAMPLE · Use case
Develop a set of campaign directions, evaluate them against a brief, and prepare a coherent creative proposal.
EXAMPLE · Use case
Investigate public supplier information, compare it against procurement criteria, and prepare an evidence-backed shortlist.
EXAMPLE · Article
Find a bounded task with a visible output, a clear review step and a useful failure mode before expanding agent access.
EXAMPLE · Article
A practical way to decide where an agent can proceed and where a person needs to review the work.
EXAMPLE · Article
Build a research brief that makes its sources and uncertainties as easy to inspect as its conclusions.
EXAMPLE · Video
An illustrative video entry showing how an agent workflow could be reviewed, with a deliberate human checkpoint.
EXAMPLE · Video
An illustrative video entry showing how an agent workflow could be reviewed, with a deliberate human checkpoint.
EXAMPLE · Use case
Compare recurring support questions with existing documentation and draft improvements for missing explanations.
EXAMPLE · Use case
Inspect proposed dependency updates, review upstream changes, and test compatibility in a disposable environment.
EXAMPLE · Use case
Review a saved reading list, follow relevant references, and prepare a concise digest tailored to stated interests.
EXAMPLE · Use case
Reconcile tasks and calendar commitments, identify conflicts, and draft a realistic weekly plan.
EXAMPLE · Use case
Inspect a repository, reproduce a reported bug, and prepare a tested patch for review.
EXAMPLE · Use case
Expand a story brief into a scene sequence, check continuity, and create a production-ready storyboard outline.
EXAMPLE · Use case
Investigate a defined question across multiple sources and produce a brief with traceable claims.
EXAMPLE · Use case
Review incoming messages, gather missing context, and turn requests into a prioritized queue of draft actions.
EXAMPLE · Use case
Monitor a bounded set of public information sources and explain changes against an established baseline.