Skip to main content
Magnitude uses a team lead + subagent model. The team lead delegates focused work to specialized agents, then combines their results into the next decision.

Agent types

All agents — including read-only ones — can read and write to the session workspace ($M). “Read-only” refers to project file access only. The workspace is shared scratch space that all agents use freely.

Explorer

  • Purpose: Investigate the codebase and gather evidence quickly.
  • Access: Read-only filesystem and shell access, web search.

Planner

  • Purpose: Evaluate approaches and produce an implementation plan. The planner considers three dimensions: velocity (fastest path to done), alignment (fits existing patterns and conventions), and capacity (leaves the system well-positioned for future changes).
  • Access: Read-only filesystem and shell access, web search.

Builder

  • Purpose: Implement code changes.
  • Access: Read-write filesystem and shell access.

Debugger

  • Purpose: Root-cause bugs through hypothesis testing. The debugger focuses on diagnosis — finding and explaining the problem — not implementing the fix.
  • Access: Read-write filesystem and shell access.

Reviewer

  • Purpose: Independently verify quality and behavior after changes. The reviewer runs tests and checks actual behavior — reading code alone isn’t considered sufficient evidence. It can spawn its own browser agents when visual verification is needed.
  • Access: Read-only verification access; can spawn browser agents when visual checks are needed.

Browser

  • Purpose: Visual browser interaction with web applications.
  • Access: Screenshot-based browser controls (click, type, scroll, navigate, tabs, evaluate JavaScript).

How subagents are used

  • The team lead chooses the right specialist for each part of a task.
  • Multiple subagents can run in parallel.
  • Subagents are reused when their context is still relevant — not always spawned fresh.
  • Each agent has tool access levels appropriate to its role.
  • Activity appears inline in the interface as agent cards, so delegation is visible as it happens.

Direct collaboration with subagents

You can message subagents directly when you need to clarify, redirect, or unblock delegated work. For the interaction workflow, see Subagents.

Lifecycle controls

Idle subagents can be closed. Closing an active subagent requires confirmation to kill it. For usage guidance, see Subagents.