Create and launch a BaZi reading agent
A developer used coding agents to build a BaZi reader that calculates charts, writes interpretations, and handles language detection and USDT payments.
Codex
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.
Use agents to triage Jira, review PRs, and send updates
Luke set up several Hermes agents to handle tickets, code, reviews, and updates while they focused on other work.
Hermes Agent
Split a migration into parallel agent tasks
A developer used Devin to break a React Native-to-Swift migration into separate tracks and run them at the same time.
Devin
Use Claude Code to hunt flaky CI tests overnight
Claude Code tracked CI flakiness, isolated the worst tests, and suggested fixes while a human reviewed the changes each day.
Claude Code
Build a book-sharing app and demo in one day
During a 24-hour hackathon, they used Replit Agent to create GiveABook and its demo video.
Replit Agent
Have an agent rebuild and extend your app
Replit Agent recreated a full-stack product, added seven RAG features, and produced a demo video in about 12 hours.
Replit Agent
Record a feature walkthrough, fix issues, and land the PR
Ryan Carson used Devin to click through a feature, find bugs, repair them, and merge the pull request with a command.
Devin
Plan a phased cloud migration with checkpoints
Use an agent to break a large migration into approved phases and carry out each step test-first.
Gemini
Rebuild Claude hooks as a pi extension
A developer had an agent convert a folder of Claude Code hooks into a pi extension after switching tools.
Claude Code
Use Claude Code to revive an old assembly build
A developer used Claude Code to get a 1991 assembly game’s old tools compiling again on modern setup files.
Claude Code
Coordinate Terraform and GitOps work with OpenClaw
A developer used multiple OpenClaw agents to handle infrastructure, coding, and GitOps tasks while directing the work in Telegram.
OpenClaw
Build new agent features inside a guarded Docker sandbox
A Claude-based agent updated its own code in Docker, with every edit checked, committed, or undone automatically.
Claude
Repair a broken API site with step-by-step review
A developer used Claude Cowork to inspect an API site, explain the trouble, and make direct code fixes after another agent kept making things worse.
Claude Cowork
Use Devin to push backlog work into pull requests
Ryan Carson used Devin across several tools to turn backlog items into pull requests faster.
Devin
Use an AI spec to brief a coding agent
Work out a feature with an AI assistant, then pass the spec to a coding agent and verify the result by testing.
ChatGPT
Deploy safely and scan exposed ports from Telegram
A security professional used an OpenClaw agent to handle deploys and port checks while keeping production changes gated by approval.
OpenClaw
Control Claude Code by voice while you work hands-free
A developer built a local spoken-command setup around Claude Code and used it to fix a WhatsApp integration without touching the keyboard.
Claude Code
Use ChatGPT to narrow down Swift error causes
A Swift developer pastes an error and nearby code into ChatGPT to get a quick first guess, then checks the output before changing anything.
ChatGPT
Use an agent to find missing database indexes
A developer had Cursor inspect a slow NestJS page and suggest database indexes to fix a production-only slowdown.
Cursor
Build a PR dashboard across multiple repos
They used ChatGPT for planning and an agent in WebStorm to assemble a dashboard that tracked pull requests across four Azure DevOps repos.
ChatGPT
Have agents co-build a reference system with role splits
A solo founder divided an AI-assisted build into roles and shipped a 120-model mental-models framework with an MCP server.
ClaudeChatGPTCursor
Run Postman endpoint tests and summarize the results
They used Comet to build test payloads from context, execute Postman requests, and return a short report.
Perplexity Comet
Create and launch a meeting app from one prompt
Replit Agent built and deployed a meeting management app with dashboards, tracking, templates, and analytics from a single prompt.
Replit Agent
Let your agent patch its own repo
A developer reported that their custom agent made its first code edit in its own repository.
Custom agent