As AI coding agents generate vast amounts of code, the most tedious part of a developer's job shifts from writing code to reviewing it. This creates a new product opportunity: building tools that help developers validate and build confidence in AI-written code, making the review process less of a chore.

Instead of manual user testing, prompt an AI agent to adopt specific user personas, like a hurried product manager or a spec-focused engineer. The AI will then use your application from that persona's perspective, providing targeted, research-style feedback on friction points and user experience.

To trust AI-generated code, Krieger’s team requires pull requests to include visual proof, such as a "full screenshot gallery of the full UI." This allows human reviewers to quickly spot issues in error states or animations that code review alone would miss, tightening the development loop.

Use Playwright to give Claude Code control over a browser for testing. The AI can run tests, visually identify bugs, and then immediately access the codebase to fix the issue and re-validate. This creates a powerful, automated QA and debugging loop.

When an AI coding assistant asks you to perform a manual task like checking its output, don't just comply. Instead, teach it the commands and tools (like Playwright or linters) to perform those checks itself. This creates more robust, self-correcting automation loops and increases the agent's autonomy.

To ensure comprehension of AI-generated code, developer Terry Lynn created a "rubber duck" rule in his AI tool. This prompts the AI to explain code sections and even create pop quizzes about specific functions. This turns the development process into an active learning tool, ensuring he deeply understands the code he's shipping.

To get the best results from an AI agent, provide it with a mechanism to verify its own output. For coding, this means letting it run tests or see a rendered webpage. This feedback loop is crucial, like allowing a painter to see their canvas instead of working blindfolded.

An agent's effectiveness is limited by its ability to validate its own output. By building in rigorous, continuous validation—using linters, tests, and even visual QA via browser dev tools—the agent follows a 'measure twice, cut once' principle, leading to much higher quality results than agents that simply generate and iterate.

Use the Claude for Chrome plugin to conduct automated user testing. Instruct the agent to perform a task within your application and observe its path. The AI can highlight confusing UI elements and provide a summary of its 'user experience,' offering a fast, low-cost way to identify usability issues.