Academy / AI Engineering with Claude

AI Engineering with Claude

Prompting to production agents — 7 levels, ~91 hours, 100% free.

This is the path I actually used. My 24-agent system that develops my own codebase came from these exact skills — read the build notes at /notes/build-org/ when you reach Level 7.
📚 Mastery Library 📈 Career OS ✓ My Learning
0/7 levels · 0%
  1. How LLMs Actually Work (~6h) — You can explain tokens, context windows, and temperature to a colleague without hand-waving.
  2. Prompt Engineering (~8h) — You write prompts that behave the same on run 10 as on run 1 — and you know how to test that.
  3. Claude API Fundamentals (~10h) — You can call the Messages API from code: system prompts, streaming, vision, and honest error handling.
  4. Structured Outputs & Tool Use (~12h) — Claude can call YOUR functions — and you know how to make it decide correctly when to.
  5. RAG — Retrieval Augmented Generation (~15h) — You can make Claude answer from YOUR documents with citations — and say 'I don't know' when it should.
  6. Agents & Orchestration (~20h) — You can design multi-step agent systems — and know when a workflow beats an agent.
  7. Production AI Systems (~20h) — Your agent survives real-world failure: dead API keys, timeouts, cost spikes, and regressions.

Capstone assignments: Triage agent with an eval harness · Retrieval bake-off lab · Cost-aware model router

After this course: Anthropic Academy courses · AI Agents Course certificate · Kaggle Learn certificates · aijobs.net · Wellfound — AI startups · lablab.ai hackathons · Upwork — AI development

Continue with: DevOps & Deployment

All free courses: Full-Stack Web Development · Digital Marketing for Builders · Python & Automation · Git & GitHub · Freelancing for Developers · TypeScript & Modern Frontend · DSA & Interview Prep · SQL & Data Analysis · DevOps & Deployment · Cybersecurity Fundamentals · UI/UX Design with Figma · Personal Branding & Content for Builders