TPEE Toptronic® Prompt Engineering Editor

23. AI Coding Workflows

Use AI for coding without breaking working software.

By Jacques Botte, founder of Toptronic®. Last updated 12 September 2026.

The lesson

Good AI coding starts with a precise task, clear file scope, tests to run, and explicit instructions not to touch unrelated code.

Use AI to explore, plan, implement, test, and review. Do not let it refactor unrelated systems just because it can.

For Rust, ask for compiler-safe changes, ownership reasoning, error handling, and minimal dependencies.

Check yourself

Question 1: What prevents AI coding from breaking unrelated work?
  1. Very vague tasks
  2. Precise scope and instructions not to touch unrelated code — correct
  3. No file paths
  4. No tests

Answer: Precise scope and instructions not to touch unrelated code

Narrow scope protects working functionality.

Question 2: What should be included for an implementation task?
  1. Tests to run and acceptance criteria — correct
  2. Only the word implement
  3. A hidden goal
  4. No constraints

Answer: Tests to run and acceptance criteria

Tests and acceptance criteria define done.

Question 3: For Rust, what should prompts emphasize?
  1. Only screenshots
  2. Ignoring warnings
  3. Unsafe by default
  4. Ownership, error handling, compiler safety, and minimal dependencies — correct

Answer: Ownership, error handling, compiler safety, and minimal dependencies

Rust work benefits from explicit safety and dependency expectations.

← Previous lesson · All 83 lessons · Next lesson →

The full course — 83 lessons and 249 quiz questions — ships inside the app. Get TPEE to study it offline.