Run coding agents in long autonomous cycles
Use a planner-worker loop with periodic review to keep coding agents moving on a large repository task.
Cursor
Agent Uses · 1,321 real examples
AI agents for coding & devops
Coding agents that build, review, test, migrate and ship software. Each entry shows what the person asked for, how it went, and a prompt to try it yourself.
The day's AI news plus 3 agent uses you can try, with ready-to-paste prompts. Free; unsubscribe anytime.
Automate a self-hosted stack on your own hardware
Jordan Fulghum let Claude Code configure and run several home services on a Beelink mini PC.
Claude Code
Move Claude Code skills into Codex
Charlie Hills used Claude Code and Codex to migrate 201 skills in an afternoon, then checked which parts worked in both tools and which still needed fixes.
Claude CodeCodex
Build a route app in tiny testable pieces
A Manus user burned through 8,100 credits and over 8 hours without finishing a working navigation app.
Manus
Run Microsoft Office on Linux with Wine
Use Wine and compatibility shims to get Microsoft 365 installing and opening on Linux without a virtual machine.
Claude Code
Draft PR reviews, then send them yourself
They used Claude Code to prepare GitHub review drafts for queued pull requests, while keeping final edits and submission under their control.
Claude Code
Have a bot test your app like a new user
Grok Bot repeatedly explored a live app, filed issues, and sketched fixes, surfacing a signup bug within two days.
Grok Bot
Flag coding conflicts before agents edit
They set up a local layer that makes coding agents announce planned changes so overlapping architecture work gets caught early.
Claude CodeCodexCursor
Auto-triage pull requests before merging them
A bot screened PRs on a schedule, routed broken ones back for fixes, and auto-merged only low-risk changes.
Grok Bot
Let an agent turn browser edits into code
A designer changed a local site in the browser while a coding agent wrote the matching CSS updates into the codebase.
Claude Code
Use parallel agents to build a database engine
They split a SQLite implementation across several coding agents working in separate branches, then merged the pieces after repeated test-and-fix loops.
Custom agent
Check a codebase for redundant packages and polyfills
An agent can scan code and install commands to find dependencies that can be replaced with built-ins or better options.
Custom agent
Assemble a R coding agent from three basic tools
They wired a Claude agent in R to file and shell helpers, then hardened it with safer path checks and editing functions.
Custom agent
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.
Custom agent
Set up a GitHub bot that triages and patches bugs
They built a GitHub bot that sorts issues, reviews pull requests, answers with citations, and opens patch PRs for humans to check.
Custom agent
Review Linux kernel patches before they land
Google’s Sashiko scans Linux kernel submissions and flags bugs that human reviewers missed.
Custom agent
Use an agent to inspect and explain COBOL on z/OS
A desktop agent connected to a mainframe to read COBOL, submit jobs, and summarize failures from spool output.
Custom agent
Deploy a project and register a domain from one agent flow
A custom agent can set up a Cloudflare account, buy a domain, and ship an app with only brief approval steps.
Custom agent
Create a fast phone agent with live voice streaming
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.
Custom agent
Track agent memory in git for coding work
Store project context in git so a coding agent can reuse decisions and notes across sessions.
Custom agent
Profile and tune a CUDA kernel with an agent
They used a LangGraph agent to test CUDA kernel tweaks, verify results, and profile candidates with Nsight.
Custom agent
Build a staged agent pipeline for PRs
Create a multi-step system that assigns issues, tests changes, and leaves the final merge to a person.
Custom agent
Translate a runtime to Rust module by module
Microsoft used agents to replace the Copilot runtime’s TypeScript with Rust while keeping the implementation’s overall design the same.
Custom agent
Use agents to benchmark and tune Rust performance
Have an agent measure Rust code, make one optimization at a time, and keep only changes that improve runtime.
Custom agent