dispatching-parallel-agents

Dispatching Parallel Agents

When you have multiple unrelated tasks (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

Core principle: Dispatch one agent per independent problem domain. Let them work concurrently.

When to Use

Multiple independent tasks?
        ↓ YES
Dispatch in parallel (3+ domains)

Use when:

• 3+ test files failing with different root causes
• Multiple subsystems broken independently
• Each problem can be understood without context from others
• No shared state between investigations

Don't use when:

• Failures are related (fix one might fix others)
• Need to understand full system state
• Agents would interfere with each other

The Pattern

1. Identify Independent Domains

Group tasks by what's broken:

• File A: Authentication logic
• File B: Data persistence
• File C: API integration

Each domain is independent.

2. Create Focused Agent Tasks

Each agent gets:

• Specific scope: One test file or subsystem
• Clear goal: What to accomplish
• Constraints: What NOT to change
• Expected output: What to return

3. Dispatch in Parallel

Agent 1 → Fix authentication tests
Agent 2 → Fix persistence tests
Agent 3 → Fix API integration tests
// All run concurrently

4. Review and Integrate

When agents return:

• Read each summary
• Verify fixes don't conflict
• Run full test suite
• Integrate all changes

Agent Prompt Structure

Good agent prompts are:

1. Focused - One clear problem domain
2. Self-contained - All context needed to understand the problem
3. Specific about output - What should the agent return?

Fix the failing tests in src/features/auth/test.ts:

1. "should authenticate valid users" - expects token in response
2. "should reject invalid credentials" - returns 200 instead of 401
3. "should handle expired tokens" - throws uncaught exception

These are logic errors in the auth handler. Your task:

1. Read the test file and understand what each test verifies
2. Identify root cause - logic errors or test errors?
3. Fix by:
   - Correcting auth handler logic if buggy
   - Fixing test expectations if testing changed behavior

Return: Summary of what you found and what you fixed.