How do you split work between several agents in one repo?
Review note: The answer refers to the original author's CV or target job offer — adapt it to your own experience.
Answer out loud or in your head first, then compare.
Answer
I assign independent scopes and agree shared contracts before the changes. If frontend and backend are to use a new format, we agree that format first. Separate branches or worktrees isolate files, but you still have to merge the result and check it together.
I don't have several agents reworking the same schema or migration at once without coordination. Each gets a goal, the context it needs and the tests. One person or process is responsible for the final merge. No Git conflict doesn't mean they work together: both parts can compile separately and not fit once merged. Parallelism should help, not multiply the integration work.
Why it matters: The practical limits of parallel work from the offer.
Possible follow-ups: How will you check a cross-cutting change after merging all the parts?
How did it go? Be honest — “Not yet” puts the question on your review list.
Start with
- I-P01 · What is an agent harness? — Harness, MCP and coding agents
- I-P02 · What is MCP? — Harness, MCP and coding agents
- I-P04 · How does a coding agent differ from a chat that suggests code? — Harness, MCP and coding agents
Further reading
- Claude Code: Create custom subagents(opens in a new tab)Docs; accessed 22.10.2026. Separate context, tools and permissions; details depend on the mode.