Stage 1 · Lesson 4 of 6
Where AI helps and where it hurts
AI tools shine on well-trodden work with a clear check: , syntax you half remember, explaining unfamiliar code, first drafts of tests, mechanical covered by tests, and finding your way around a new codebase. They struggle where the answer depends on facts they cannot see or rarely saw: your business rules, subtle concurrency, security decisions, performance under real load, new library versions, and big, vague tasks with no .
A good habit is to ask two questions before you prompt: can I check the result quickly, and do I already know what good looks like? If both answers are yes, hand it over. If not, think and , then use the tool for pieces.
Common trapasking an agent to build a whole application and then trying to understand thousands of lines afterwards.
A question to check yourself, an AI practice session and 2 cheat sheet entries come when you add the roadmap to your account. Add it
Resources for this stage
Start with· follow one of these
- VideoFreeDeep Dive into Large Language Models like ChatGPT
Andrej Karpathy · Intermediate
A clear, free explanation of how language models are trained and why they hallucinate; watch the first hour
- CourseFreeClaude Code 101
Anthropic · Beginner
Anthropic's free starter course: what an agent is, the agentic loop, context and permissions