Most coding assistants provide four interaction modes:
Inline autocomplete shows a suggestion at the cursor, usually accepted with Tab.
Chat answers questions or drafts code without changing files.
Edit mode applies a requested change to selected code or a small set of files.
Agent mode can search the repository, edit several files, run commands, and react to test failures.
Each mode gives the tool more freedom. Autocomplete is fast and has a small impact. Chat is useful for learning and discussing options. Edit mode is good for a focused change with a visible diff. Agent mode suits a clear, testable task, but it also has the largest risk.
Select the least powerful mode that can complete the job, then review everything it produces.
Rewriting in plainer words…
This answer doesn't lend itself to a diagram - it reads best . No credits were charged.
A failing test reproduces a bug. Which mode would you use to fix it, and why?Edit mode if you already know the file; agent mode if it has to find the cause and rerun the test. Either way, read the diff before accepting.
What you can say
Most coding assistants give you four modes: inline autocomplete, chat, edit mode and agent mode, and each one gives the tool more freedom than the last.
Autocomplete suggests code right at the cursor and you usually accept it with Tab, so it's fast and each suggestion has a small impact.
Chat answers questions or drafts code without touching your files, which makes it good for learning and talking through options.
Edit mode applies a change you ask for to selected code or a few files, and you get a visible diff to check.
Agent mode can search the repo, edit several files, run commands and react to test failures, so it fits a clear task you can test.
It also carries the most risk, so I pick the least powerful mode that can do the job and review everything it produces.
Weak answers to avoid
Names products instead of modesThe question asks about modes, not vendors. Most tools offer several modes, so name each one and say what it is allowed to do.
Lists four definitions with no trade-offA bare list sounds memorized. Say that freedom grows from autocomplete to agent, risk grows with it, and that this is how you pick one.
Treats agent mode as always the best choiceReaching for the most powerful mode for every task is a red flag. Say you use the least powerful mode that can do the job and review its output.
Interview lens
Likely follow-ups, what you can say, and the weak answers to avoid.
