Shipping code, reviewing PRs, running infra, and fixing things at 3am.
198 use cases
A screen-reader user asked their Muse agent to build an iCloud skill and it produced something, but accessibility problems with the text field and conversation navigation got in the way.
In an independent test, Muse Code audited 222 pull requests in under five minutes for about ten cents, but also built a plan on a Google project that doesn't exist.
A cookbook shows a GitHub bot that triages issues, reviews PRs, answers questions with citations, flags AI-slop contributions, and opens patch PRs for human review.
Gilbert Pellegrom had his OpenClaw agent build a simple idle game from a conversation, commit it to GitHub and auto-deploy it to Vercel.
A QA engineer's OpenClaw agent reads failed CI logs, classifies failures, posts analysis to GitHub and Slack and opens issues; flakiness fell from 8% to 0.8%, though it once wrongly altered an assertion.
OpenAI's internal OpenClaw agent Androidclaw uses Git, GitHub and logs to investigate broken builds, trace problems to incidents, and sometimes prepare and merge fixes.
A security professional uses an OpenClaw agent with read-only prod access, PR-only changes and manual approval for restarts to deploy changes and scan a VPS for exposed ports.
Claude Code with Claude in Chrome writes code, opens localhost, clicks through the UI, reads console errors and fixes them without the developer touching the browser.
A frontend developer pairs Claude in Chrome with Claude Code to open the app, click through it, read the DOM, check console errors and network requests, and fix UI bugs.
A developer used Claude Code computer use to compile, launch, and click through macOS app screens to find layout bugs.
A tool lets Claude Code drive an iOS app through the accessibility tree, tap every screen, and return a structured bug summary.
A developer used Claude Code as a pair programmer for provisioning, database seeding, SSL, DNS cutover and production debugging, finishing in about four hours with zero downtime by his account.
An engineer ran a proof-of-concept that consolidated 4 repos into 2, moved MySQL to PostgreSQL, upgraded frameworks and replaced the auth model, in about 15 work days.
A developer had Claude Code switch a monorepo to oxlint/oxfmt, restructure the architecture and redesign a site, validating in a loop; the redesign took days instead of weeks.
The author leaves Codex CLI running for hours to add debug prints and test hypotheses against a reproducing unit test, often only to find the bug.
Codex CLI over SSH found the OOM killer in kernel logs on a 2 GB droplet with no swap and listed fixes by risk without changing anything.
An MCP server lets Claude Code hand web navigation, login-walled pages and research to Comet while it keeps coding, then returns results.
Thoughtworks consultants used Gemini 2.5 Pro in a two-week pilot to produce validated blueprints of legacy systems' functionality.