| name | Explee Agents |
| description | Run Explee pre-built and custom AI agents, then poll run status and return structured outputs. USE WHEN running agent workflows for extraction, reasoning, or automation. |
Explee Agents
Use this skill for extraction, reasoning, and automation tasks powered by Explee Agents.
Auth & endpoints: see explee-api-core. List uses T1, runs use T3, polls use T4.
Endpoints (this product)
GET /public/api/v1/agents — list agents + input_schemaPOST /public/api/v1/agents/{agent_id}/runs — run a pre-built agentPOST /public/api/v1/agents/runs — run a custom agentGET /public/api/v1/agents/runs/{run_id} — poll a run
Execution Pattern
- List available agents and inspect each
input_schema.
- Choose a pre-built agent if available; otherwise run a custom agent.
- Submit a run with minimal valid input.
- Poll until completion, then return a normalized result.
Request Body (the unique part)
Run a pre-built agent (<agent_id> in the path, template T3):
{"input":{}}
Product-specific notes
- Validate the payload against the returned
input_schema before running.
- For custom agents, keep system prompts concise and deterministic.
- Always report the run lifecycle:
pending → completed / failed.
