Free PDF · 12 pages · October 2026
AI Engineering Cheat Sheet
What our labs measured about tokens, prompting, RAG, evals, agents, serving, cost and fine-tuning, and the rule each result teaches.
What is inside
- Tokens and embeddings, and prompting that holds up
- RAG: chunk size and overlap measured, embeddings, HNSW, hybrid search and reranking
- Evals: error analysis first, and the ways an LLM judge misleads you
- Agents in production, serving and inference, and where the cost goes
- Fine-tuning: when it pays, and why production breaks
Each result comes from a lab in the AI Engineering course, with the model it ran on. Every lesson is linked, so you can read how it was measured.
Two courses by the author of this page:
204 lessons · 10 free to read
₹999 in India · $49 elsewhere, once
Get AI EngineeringYou own this course
770 lessons · 18 free to read
₹499 in India · $49 elsewhere, once
Get System DesignYou own this course
Every lesson in both courses has an AI tutor beside it. It reads the same lesson you are reading and answers your questions from it. Try the tutor



Real pages from the PDF