agent-designer

原文涵盖的主题

• Agent Designer — Multi-Agent System Architecture
• When to use
• Pattern decision table
• Workflow
• 1. Design the architecture
• 2. Generate tool schemas
• 3. Evaluate execution logs
• 4. Verification loop

Design, schema-generate, and evaluate multi-agent systems with three deterministic tools. The scripts are the workflow — do not freehand an architecture when the planner can score one from requirements. Designing a new multi-agent system from requirements (pattern choice, roles, comms) Generating provider-ready tool schemas (Anthropic + OpenAI formats) from plain tool descriptions Evaluating execution logs: success rate, latency distribution, cost, bottlenecks When NOT to use: Claude Code Workflow-tool automations → workflow-builder; single-agent workflow scaffolds → agent-workflow-designer; multi-agent fan-out at runtime → agenthub. | Choose | When | Watch out for | |---|---|---| | Single agent | One bounded task, 8 agents | Communication overhead per level | | Swarm | Parallel peers, fault tolerance over predictability | Hard to debug; needs consensus rules | The planner applies this scoring deterministically — run it rather than picking by feel. All paths relative to this skill folder. Each step's JSON output is the next step's design input. Write a requirements JSON (copy assets/samplesystemrequirements.json — keys: goal, tasks[], constraints{maxresponsetime, budgetpertask, con

这里只展示节选，请以完整原文和当前要求为准。