Path 01 · 6 lessons · 54 min
Understand AI development
Explore ideas with the tools that suit the task. Learn what to check before a prototype gets real data or permissions.
- 01
Vibe coding: uses and limits
Help people explore ideas with AI. Use a banking prototype to understand why live data and API permissions need security evidence.
- 02
Models, context, and incorrect answers
Identify how missing information can cause an incorrect answer, even from a capable model.
- 03
Assistants, agents, and permissions
Distinguish an answer from an action. Identify the tools and permissions that change the consequences of a mistake.
- 04
Choose a useful first AI task
Select a small task with clear inputs, visible results, and limited consequences.
- 05
Measure useful progress
Measure completed work, review effort, and rework. Do not use generated code volume as a measure of value.
- 06
Choose a model with evidence
Compare models on representative tasks, acceptance criteria, cost, and the operating constraints of your team.