Claude Code
Best for: Serious work on real repos
Anthropic's agent for your terminal, IDE and desktop. Reads the whole repo, runs commands and tests, and handles large multi-file changes well.
Visit Claude Code ↗Home / Use case
Get AI to write tests for your app
“I have almost no tests and I'm afraid to change anything.”
AI can write browser tests, API checks and unit tests fast. Run each new test several times to catch flaky ones, and make sure it actually fails when the code is broken.
Fix it yourself in 3 steps
- List the 5 flows that would hurt most if they broke.
- Ask the AI to write one test per flow, run them, and show results.
- Break something on purpose to confirm a test catches it; keep test logins out of git.
Copy this prompt
Write automated tests for these flows: [list], using [Playwright/pytest/etc.]. Run each test 5 times and report flakiness. For one test, show it failing when I break the feature on purpose. Keep any saved login sessions in a git-ignored folder. Stop after the report.
Fill in the [brackets]. Each prompt says when the AI should stop, so it doesn't wander off.
Agents people used for this: Perplexity Comet, Claude Code, Codex.
Inspired by real examples collected at agentusecases.ai.
📚 3 real stories of people doing this with AI agents
- Find bugs with property-testing agent swarms · Codex
- Test API endpoints in Postman and report results · Perplexity Comet
- Write Playwright tests with Playwright MCP and Claude Code · Claude Code
Collected at AgentUseCases.ai.
Tools for this
OpenAI Codex
Best for: Delegating tasks as PRs
OpenAI's coding agent, in the CLI and in the cloud. Good at handing off well-scoped tasks that come back as pull requests.
Visit OpenAI Codex ↗Perplexity
Best for: Research with citations
An answer engine that searches the web and cites its sources. Built for research questions.
Visit Perplexity ↗