B2Beginner 45 minutes reading and codeLocked

Few-Shot, Chain-of-Thought, Tree-of-Thought

Telling a model what to do is prompting. Showing it how to think is engineering. The gap between 78% and 91% accuracy on the same model, same task, same data is not a better model. It is a better reasoning strategy.

In this lesson

  1. 01Learning Objectives
  2. 02The Problem
  3. 03The Concept
  4. 04Build it
  5. 05Use it
  6. 06Exercises
  7. 07Key Terms
  8. 08Further Reading
  9. 09Role
  10. 10Task
  11. 11Input
  12. 12Rules

About 3900 words of reading, with code, 5 quiz questions and the tutor.

The full lesson opens with an access code

You can see what this lesson covers and the milestone it sets. The full text, code, quizzes, the tutor and the AI reviews come with the K850 practice, along with weekly build sessions and code review.

Codes come with the K850 practice. Book a place

Book the K850 practiceRead an open lesson

Milestone forThe ZRA Tax Desk

Teach it the shape of a good tax answer

Add few-shot examples of excellent answers (short, cited, with the next step) and one example of a correct refusal. Compare zero-shot, few-shot and chain-of-thought on your 15 questions and keep what wins.

Done when

  • Three worked examples and one refusal example, each under 120 words
  • Zero-shot, few-shot and CoT scored on the same 15 questions with a table
  • The shipped strategy beats zero-shot by at least 2 passes, or you explain why not

Stretch: Measure token cost of each strategy and include it in the decision

Reviews open with an access code.

Interview practice

Questions on this topic that AI engineering interviews ask, with the companies reported to ask them. Answer the way you would out loud; Jev scores it and DeepSeek tells you what to add.

Scoring opens with an access code. You can still read the questions and prepare.

B1Prompt Engineering: Techniques & PatternsNext · B3Structured Outputs: JSON, Schema Validation, Constrained Decoding

Adapted from open-source work: AI Engineering from Scratch by Rohit Ghumare (MIT, lesson text, code and quizzes); Awesome LLM Apps by Shubham Saboo (Apache-2.0, starter code); AI Engineering Interview Questions by Outcome School (Apache-2.0, interview questions). Capstones, milestones, data packs and Zambian context by Zambrite.

Chat on WhatsApp