Create a CLI coding agent from a Python LLM base
Claude Code turned Simon Willison’s Python LLM template into a working CLI coding agent from two prompts.
Agent Uses · 1,321 real examples
Real examples of people putting Custom agent to work: the task, how it went, what to watch out for, and a prompt you can adapt.
The day's AI news plus 3 agent uses you can try, with ready-to-paste prompts. Free; unsubscribe anytime.
Claude Code turned Simon Willison’s Python LLM template into a working CLI coding agent from two prompts.
An agent checked a flight’s timing, estimated the payout, and drafted the airline claim without submitting it.
Run coding agents through your product’s onboarding and get a scorecard, fix list, and session traces.
An Instacart assistant filled a cart from prior shopping history, then added meal ingredients and pointed out missing store items.
A group built a math environment where agents chose their own leads, ran tests, and shared findings without a central planner.
Graphify C# helps agents map real C# usages, including overrides and implementations, from compiler-resolved project data.
Use a coding agent with Graphene to define metrics, query your warehouse, and publish a report with charts and screenshots.
A parent has an agent sort school mail, summarize it, and draft responses they can review before sending.
Small businesses set up voice agents to screen calls, capture details, and route real customers to staff while logging everything in their CRM.
A Claude Opus 5.5 agent team screened Luttinger-compensated magnets and surfaced two predicted room-temperature magnetic semiconductor candidates.
Store project context in git so a coding agent can reuse decisions and notes across sessions.
They set up agents to take late calls, gather details, book appointments, and spot upset callers for follow-up.
They built a multi-agent setup that weighs a stock from several angles, then routes a recommendation through review stages before any simulated order is sent.
A staffing firm used a voice agent to reach candidates, ask screening questions, and book recruiter interviews.
A custom agent kept one investment project alive, saving models and notes so later sessions could pick up where the last run stopped.
An AI agent handled a GoDaddy support chat and secured a cheaper price after the person set the rules and waited for the result.
They assembled a call-answering agent with live transcription, generation, and speech output, then moved it closer to the services to get about 400ms latency.
They built a retail site with AI, added checkout, and verified the payment flow before turning it into a live store.
A custom agent used figma-use to generate Figma design elements and reusable UI pieces from a terminal.
An agent ran 365 short rounds, checked a revenue dashboard each time, and ended up with 394 linked pages plus a webhook checker site.
They built a GitHub bot that sorts issues, reviews pull requests, answers with citations, and opens patch PRs for humans to check.
Stripe uses in-house coding agents to carry tasks from ticket to reviewable code, then humans check the result.
AI Village let agents choose their own games, and one agent spent the week on Minesweeper while also keeping a shared score sheet.
A developer made a quiet agent that checks calendar time against goals, then began adding email triage when users wanted more automation.