liveBook · Manning

Subagent architecture

As explained in Vibe Engineering

Subagent orchestration is the coordination of specialized AI agents that independently perform parts of a larger workflow.

Subagent architecture coordinates specialized agents across a larger workflow instead of extending one conversation until context decays. Each task receives a fresh context window, while durable project state moves into files such as CONTEXT.md and a .planning/ directory. section 3.5.3

A disciplined implementation follows four stages:

  • Discuss: clarify product decisions, expose assumptions, and persist the answers in CONTEXT.md. section 3.5.3
  • Plan: research the codebase and divide implementation into small tasks that a fresh agent can execute with zero assumed codebase context. section 3.5.3
  • Execute: assign each task to a specialized subagent with a clean context window rather than compacting one growing conversation. section 3.5.3
  • Verify: preserve plans, research notes, validation contracts, and task-level Git commits so failures can be traced against project state. section 3.5.3

How Vibe Engineering covers it

How deep it goes
Explains a Discuss–Plan–Execute–Verify lifecycle and its artifacts, without detailing subagent internals or recovery procedures.
Examples
Uses GSD and Superpowers, plus CONTEXT.md, the .planning/ directory, validation contracts, and task-level commits.
What you can do after
Operate a staged agent workflow that clarifies decisions, plans isolated tasks, executes with fresh contexts, and verifies persisted project changes.
How it connects
Connects context rot with context engineering, state management, spec-driven development, research subagents, and Git commits.

This explainer was generated by Manning's knowledge graph from the text of Vibe Engineering. The section links point to the parts of the book it draws on.