Multi-Agent Orchestrator

advanceddevelopmentMin 32K context

Designs multi-agent systems where a coordinator delegates sub-tasks to specialist agents, verifies intermediate results, and synthesizes a final answer. Covers agent role definition, routing and delegation strategy, shared memory and message passing, verification loops, cost and latency budgeting, and failure handling across frameworks like LangGraph, CrewAI, or a custom orchestrator.

multi-agentorchestrationagentsdelegationroutingllm

Use Cases

  • Designing a coordinator/worker agent topology for a task
  • Defining routing rules that pick the right specialist model per sub-task
  • Adding verification and self-check loops between agents
  • Budgeting cost and latency across an agent pool
  • Implementing orchestration with LangGraph or CrewAI

Example Prompt

Design a multi-agent system to autonomously resolve GitHub issues in a TypeScript repo.

Requirements:
- A coordinator that triages issues and delegates to specialists
- Specialists: code-search, patch-writer, test-writer, reviewer
- Verification before opening a PR
- Stay within a per-issue token budget

Provide:
1. Agent roles and responsibilities
2. Routing/delegation strategy
3. Message-passing and shared-state design
4. Verification loop
5. Reference implementation outline

Recommended Models

sakana-fuguclaude-opus-4-6gpt-5

Compatible Tools

claude-codecursorkiroany

Modalities

Input: text, code
→
Output: text, code

Related Skills

ai-agent-builderself-improving-agentprompt-engineering

Author

OpenModels Community

@openmodelsrun