| name | dispatching-parallel-agents |
| description | Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies |
Dispatching Parallel Agents
Overview
When you have multiple unrelated failures or tasks, 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
Use when:
- 3+ failures 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
- Need to understand full system state
- Agents would interfere with each other
The Pattern
1. Identify Independent Domains
Group failures by what's broken.
2. Create Focused Agent Tasks
Each agent gets:
- specific scope
- clear goal
- constraints
- expected output
3. Dispatch in Parallel
Run one task per independent domain.
4. Review and Integrate
When agents return:
- read each summary
- verify fixes don't conflict
- run full verification
- integrate all changes
Common Mistakes
- Too broad task prompts
- No context in prompts
- No constraints
- Vague expected output
Verification
After agents return:
- Review each summary
- Check for conflicts
- Run full suite/checks
- Spot check
