Engineering
Agents that write unit, integration and end-to-end tests, raise coverage and fix flaky suites.
14 published use cases
Claude Code reads your coverage report, picks the riskiest untested modules and writes unit tests that pass, one small PR at a time.
An OpenProject setup that auto-assigns work packages to AI agents, runs QA review on pull requests, and closes tickets when they pass.
Via Hacker News · kookster310 ↗A Grok Bot clicked through an app's core flows several times a day, reported problems and drafted fix PRs; it found a real bug.
Original post ↗A walkthrough of using Playwright MCP with Claude Code to generate Playwright tests in minutes.
Original post ↗Claude monitors CI pass rates, identifies worst flaky tests, reproduces them and proposes fixes overnight; pipeline got 20 minutes faster and pass rate rose 35%, with some bad fixes discarded.
Original post ↗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.
Original post ↗Used Replit Agent to build a /help page that generates tutorial videos via scenes, Playwright recording, TTS narration and ffmpeg stitching.
Original post ↗A how-to guide shows Microsoft Scout driving a Playwright browser from a prompt to scrape sites, capture screenshots, fill forms and export data.
Original post ↗Grok handled live chat, email, tickets, refunds, knowledge base, QA, reporting and escalations for an 8-person support company, per the author's account.
Original post ↗Claude restructured an accelerated math curriculum into one year, writing tests, games, worksheets, a schedule, and a hosted site integrated with a teacher planner.
Original post ↗Codex made a racing game with multiple racers, eight maps and items from one prompt, acting as designer, developer and QA tester by playing it.
Original post ↗A developer wired Gemini's Computer Use model to Playwright in Java and had it play a simple button-clicking game to verify click-coordinate scaling.
Original post ↗A researcher used Claude Opus in Claude Code with Playwright MCP to decompile code, find vulnerabilities, and build a working exploit.
Original post ↗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.
Original post ↗They are a fast way to raise coverage, but check that each test asserts real behaviour rather than mirroring the current code. Run them in CI and review failures the same way you would for tests a teammate wrote.
Across the 14 published workflows on this page, the most used tools are Claude Code (5), Codex (2) and Grok Bot (2). Each use case lists every tool it needs and the role it plays.
Open any use case to see the tools, the step-by-step setup and example prompts you can copy. Start with a beginner workflow, run it on a small batch and review the output before you automate it fully.