Build

Playground

Run a reasoning agent: it samples, critiques or judges before it answers.

Reasoning agents need a Pro or Premium plan. Requests from a free-tier key return 403. See plans

Reasoning agent

Evaluate another model’s or agent’s output against domain criteria. How it works

196
Ready: Agent Judge · gpt-5.5

Nothing yet

Pick a reasoning agent, write a task, then click Run agent.

Request preview

curl -X POST 'https://api.swarms.world/v1/reasoning-agent/completions' \  -H 'x-api-key: '"$SWARMS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "agent_name": "output-judge",  "description": "Evaluates an answer for accuracy and completeness.",  "swarm_type": "AgentJudge",  "model_name": "gpt-5.5",  "max_loops": 1,  "task": "Evaluate this answer for accuracy and completeness.\n\nQuestion: What causes the seasons on Earth?\nAnswer: The seasons happen because Earth is closer to the Sun in summer and farther away in winter."}'
Playground: Run Multi-Agent Swarms in Your Browser — Swarms Cloud