11 Things I learned after using AI Agents full-time
This title could be clearer and more informative.Try out Clickbait Shieldfor free (5 uses left this month).
AI agents like Cursor have transformed app development workflows through deliberate practices. Key learnings include using plan mode before execution to clarify intent, maintaining custom GPT projects for context continuity, leveraging agent skills instead of lengthy AGENTS.md files, choosing reasoning models for complex tasks, breaking large prompts into focused scopes, reviewing AI-generated code carefully to prevent tech debt, learning tools deeply to find leverage points, implementing linters and rules as guardrails, evolving AGENTS files to prevent recurring mistakes, running tests and CI on every PR, and exploring uncomfortable tools to discover new capabilities. The core insight: AI agents amplify both discipline and shortcuts, multiplying responsibility rather than removing it.
Table of contents
1. Not using plan mode2. Treating prompts as one-offs3. Ignoring skills4. Letting the model decide everything5. Prompting everything at once6. Not reviewing changes carefully7. Not learning the AI development tools deeply8. No hooks. No rules. No guardrails9. Forgetting to evolve my AGENTS file10. Skipping tests and CI in PRs11. Avoiding discomfortConclusion2 Comments
Sort: