Dispatching Parallel Agents

Dispatching Parallel Agents

Quick Start

1. Analyze - Identify independent vs dependent tasks
2. Group - Create parallel groups with no shared dependencies
3. Specialize - Assign agents by expertise (explorer, implementer, reviewer)
4. Dispatch - Fan-out tasks with timeouts and concurrency limits
5. Aggregate - Combine results using merge, consensus, or priority
6. Handle Errors - Retry failed, continue with partial, or fail-fast

Features

Common Patterns

# Parallel Execution Model
         [Main Agent (Orchestrator)]
                    |
         [Task Analysis & Distribution]
                    |
    +---------------+---------------+
    |               |               |
[Agent A]      [Agent B]      [Agent C]
(Task 1)       (Task 2)       (Task 3)
    |               |               |
    +-------+-------+-------+-------+
            |
    [Aggregation & Integration]
            |
      [Final Response]

TIMING:
Sequential: ████████████████████████████
Parallel:   ████████████  (max of tasks)

// Fan-out/Fan-in Pattern
const [security, performance, style] = await Promise.all([
  spawnAgent({ type: 'reviewer', focus: 'security' }),
  spawnAgent({ type: 'reviewer', focus: 'performance' }),
  spawnAgent({ type: 'reviewer', focus: 'style' }),
]);
return combineReviews([security, performance, style]);

// Parallelization Criteria
CAN PARALLELIZE:
- Independent code changes (different files)
- Research on different topics
- Tests for different modules
- Multi-concern code reviews

CANNOT PARALLELIZE:
- Tasks with data dependencies
- Sequential workflow steps
- Tasks modifying same files
- Tasks sharing mutable state

# Agent Specialization
| Type | Strengths | Best For |
|------|-----------|----------|
| explorer | Finding files, patterns | Initial exploration |
| implementer | Writing production code | Features, bug fixes |
| tester | Test design, edge cases | Unit/integration tests |
| reviewer | Issue identification | Code review, security |
| documenter | Clear explanations | Docs, comments |

Best Practices

Related Skills

• optimizing-tokens - Efficient context per agent
• thinking-sequentially - Order dependent tasks
• writing-plans - Plan parallel execution phases
• executing-plans - Execute with parallel steps

Converted and distributed by TomeVault — claim your Tome and manage your conversions.