LLearnCode
Academy/AI fluency & verification

production · 40 lessons

AI fluency & verification

Prompt Repair, AI Engine Lab, and practical judgment about generated work.

What you are working toward

Treat AI output as a hypothesis until verified.

0 learning steps complete · View prerequisites and evidence →

The existing foundation

Start here, or use it to fill a gap.

Original lessons, practice, bosses, and progress are preserved. Completion from this journey is distinct from the new independent evidence model.

  1. 01GoalGuided foundationOpen →
  2. 02ContextGuided foundationOpen →
  3. 03SourceGuided foundationOpen →
  4. 04ExpectationsGuided foundationOpen →
  5. 05GCOS assemblyGuided foundationOpen →
  6. 06ConstraintsGuided foundationOpen →
  7. 07Output contractGuided foundationOpen →
  8. 08ExamplesGuided foundationOpen →
  9. 09DecompositionGuided foundationOpen →
  10. 10Critique loopGuided foundationOpen →
  11. 11VerificationGuided foundationOpen →
  12. 12Uncertainty handlingGuided foundationOpen →
  13. 13Tool-aware promptingGuided foundationOpen →
  14. 14Source quality & conflictsGuided foundationOpen →
  15. 15Privacy & sensitive contextGuided foundationOpen →
  16. 16Untrusted instructions & prompt injectionGuided foundationOpen →
  17. 17Prompt debuggingGuided foundationOpen →
  18. 18Research promptsGuided foundationOpen →
  19. 19Coding promptsGuided foundationOpen →
  20. 20Analysis promptsGuided foundationOpen →
  21. 21Writing promptsGuided foundationOpen →
  22. 22Prompt evaluationGuided foundationOpen →
  23. 23Agentic workflowsGuided foundationOpen →
  24. 24Reusable prompt systemsGuided foundationOpen →
  25. 25What is AI?Guided foundationOpen →
  26. 26Model, app, assistant or agent?Guided foundationOpen →
  27. 27Different kinds of AIGuided foundationOpen →
  28. 28Tokens: the pieces AI readsGuided foundationOpen →
  29. 29Context window: AI's working deskGuided foundationOpen →
  30. 30How models learnGuided foundationOpen →
  31. 31Parameters: learned weightsGuided foundationOpen →
  32. 32How an LLM generates textGuided foundationOpen →
  33. 33Attention: relating pieces of contextGuided foundationOpen →
  34. 34Embeddings: meaning as coordinatesGuided foundationOpen →
  35. 35RAG: model memory vs retrieved factsGuided foundationOpen →
  36. 36Why AI can answer differentlyGuided foundationOpen →
  37. 37Multimodal AIGuided foundationOpen →
  38. 38Reasoning, tools and agentsGuided foundationOpen →
  39. 39Why AI can be confidently wrongGuided foundationOpen →
  40. 40What happens to your prompt data?Guided foundationOpen →
Open interactive labs →Explore capstonesOriginal academy boss →