Working with AI coding assistants and agents
Comes up in: AI-assisted coding, Behavioural
This concept is being written. It gets the full five steps — explanation, predict, interview angle, practice with tests, and review cards. Here is exactly what it will cover, so you can study it elsewhere in the meantime.
What it covers
- autocomplete vs chat vs agentic coding tools
- giving good context (specs, tests, constraints)
- small verifiable steps
- reading every line
- tests first so AI output is checked
- where AI is weak (subtle concurrency, security, new APIs past its training data)
Words you will know
What you will practise
- implement a feature with an AI tool, logging every correction you made
Interview questions this answers
- How do you use AI tools in your daily work? How do you check their output?
- What kinds of bugs do AI coding tools commonly introduce?