An AI assistant for long documents, analysis and code, with Claude Code and Cowork on paid plans.
QA engineer
ChangingAI now writes test cases and automated tests from a description, while the tester decides what to check and finds bugs where the script didn't expect any. A new area of work: testing the AI features inside the product itself.
Where this job sits on the map
In the same group: 78 of 100 professions.
What changes
AI writes test cases and automated tests from requirements in minutes.
Agents walk through scenarios in a browser on their own and report failures.
There's a new task: checking a product's AI features for errors and made-up answers.
AI drafts, the person decides
How the work splits here: AI prepares a draft, the person checks it and makes the call.
What AI does
- Writes test cases from requirements and mockups
- Writes automated browser tests
- Formats bug reports from steps and screenshots
- Comes up with test data, including edge cases
What stays with the person
- Deciding what's important to test and where the risk to the user is
- Exploratory testing: finding bugs nobody expected
- The last word before a release
- Checking AI features for errors, harmful answers and made-up ones
What to learn first
5 lessons from the course, in order. Start with the first one.
- How to write a good promptUserHow to give AI a task: the five parts of a good prompt, Plan Mode, and how to refine an answer instead of starting over.Start here
- AI ethics and safety: hallucinations, attacks, biasUserHallucinations, prompt injection, bias, privacy and copyright: how not to trust AI blindly.
- Browser automation: Playwright + QABuilderBrowser automation: Playwright and Claude in Chrome for testing forms and checking your own websites.
- Evals: skills that improve themselvesEngineerEvals for skills: tests, pass rate, checking that the skill triggers and a data-driven improvement loop.
- Prompt injection defense, the top security threat of 2026EngineerPrompt injection: six attack types, eight layers of defense, red team tests and an incident response plan.
Which tools to use
- Freemium
Anthropic's coding agent for the terminal, your IDE and a desktop app, included in paid Claude plans.
PaidA VS Code-based code editor with AI agents, a free Hobby plan and Pro at $20 a month.
FreemiumA general-purpose AI agent: research, websites, slides and browser automation.
Freemium
Ready-to-use materials
- How to check an AI answerChecklist
Assess the risk, spot the signs of a made-up answer and run a 5-minute check before you act on what AI says.
Free Go through an AI answer claim by claim: what's right, what's doubtful, where it's wrong and what to check at the source.
Free- Before you launch a productChecklist
27 items: payments, analytics, legal basics, support, launch day and a review one week later.
Free
How to earn with AI
We don't promise income: results depend on your niche, your market and your work.
- Job
Give AI the routine test cases and automated tests, and invest your time in exploratory testing and checking AI features.
- Service
Pre-launch testing for small business websites and apps: forms, payments, the mobile version, and a report with a prioritized fix list.
- Product
A set of checklists and test scenarios for common products: an online store, online booking, a chatbot.
Similar professions
Checked: October 2026