According to Anthropic's Claude Code team, the most valuable part of an AI agent's "Skill" is often a "Gotcha Section." This explicitly details common failure points and edge cases. This practice focuses on encoding hard-won experience to prevent repeated mistakes, proving more valuable than simply outlining a correct process.

When an AI tool makes a mistake, treat it as a learning opportunity for the system. Ask the AI to reflect on why it failed, such as a flaw in its system prompt or tooling. Then, update the underlying documentation and prompts to prevent that specific class of error from happening again in the future.

The key skill for an AI PM is knowing a model's current capabilities. This is built by intensely using the model and, crucially, asking it to introspect on its own unexpected behaviors to understand *why* it made a mistake, revealing gaps to fix.

Expect your AI agent's skills to fail initially. Treat each failure as a learning opportunity. Work with the agent to identify and fix the error, then instruct it to update the original skill file with the solution. This recursive process makes the skill more robust over time.

A powerful evaluation technique is to ask an AI agent to analyze its own poor output. The agent can review its context and process, explain why it made a mistake, and even suggest how to update its own instructions to prevent future errors.

Borrowing from classic management theory, the most effective way to use AI agents is to fix problems at the earliest 'lowest value stage'. This means rigorously reviewing the agent's proposed plan *before* it writes any code, preventing costly rework later on.

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.

When reviewing work, an AI-native leader's role shifts. Instead of repeatedly giving the same feedback (e.g., "put the CTA above the fold"), they should fix the underlying AI skill, prompt, or design system that caused the error, thus automating the correction for all future work.