What problem does it solve?
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.
Core Features & Use Cases
- Core principle: Dispatch one agent per independent problem domain. Let them work concurrently.
- When to Use:
- 3+ independent tasks across files or subsystems that can be worked on concurrently without shared state
- Multiple subsystems broken independently
- Each problem can be understood without context from others
- Don't use when:
- Failures are related (a single root cause)
- You need full system state understanding
- Shared state would cause interference
- The Pattern:
- 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.
- 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
- Dispatch in Parallel
Agent 1 → Fix authentication tests
Agent 2 → Fix persistence tests
Agent 3 → Fix API integration tests
// All run concurrently
- 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:
- Focused - One clear problem domain
- Self-contained - All context needed to understand the problem
- Specific about output - What should the agent return?
Then provide a sample:
Agent prompts should clearly specify the target files, the scope, constraints, and expected outputs.
Quick Start
Define 3+ independent domains and assign each to a dedicated agent to run concurrently, then review and merge results.
