Run | Labric | Documentation

curl -X POST https://platform.labric.co/api/v1/agent/runs \
     -H "Authorization: Bearer <api_key>" \
     -H "Content-Type: application/json" \
     -d '{
  "prompt": "Which samples from the latest XRD batch show the strongest primary diffraction peak, and how does that compare to the previous batch?"
}'

{
  "output": "In batch XRD-2024-06, sample TF-0612 shows the strongest primary reflection at 2θ = 38.2° with 42,300 counts, followed by TF-0608 at 39,800 counts. The batch median peak intensity is 12% higher than batch XRD-2024-05, consistent with the improved crystallinity expected from the longer annealing step.",
  "model": "claude-opus-5",
  "tool_calls": [
    {
      "tool_call_id": "toolu_01Xk8dQe2RfLmN4vTgH6sJwB",
      "tool_name": "sql_schema_get",
      "input": {},
      "output": {
        "success": true,
        "tableCount": 12
      }
    },
    {
      "tool_call_id": "toolu_01Ym3cVa7PdKqR9nWbE5tLzF",
      "tool_name": "sql_query_run",
      "input": {
        "query": "SELECT sample_name, batch_id, peak_two_theta, peak_intensity FROM xrd_measurements WHERE batch_id IN ('XRD-2024-06', 'XRD-2024-05') ORDER BY peak_intensity DESC"
      },
      "output": {
        "results": {
          "columns": [
            "sample_name",
            "batch_id",
            "peak_two_theta",
            "peak_intensity"
          ],
          "data": [
            [
              "TF-0612",
              "XRD-2024-06",
              38.2,
              42300
            ],
            [
              "TF-0608",
              "XRD-2024-06",
              38.2,
              39800
            ]
          ]
        },
        "rowCount": 48,
        "success": true
      }
    }
  ],
  "usage": {
    "input_tokens": 5210,
    "output_tokens": 412,
    "total_tokens": 5622
  },
  "chat_id": null
}

Run the Labric data-analysis agent and return its final answer alongside the tool calls it made. With stream=true the response is instead a stream of server-sent AgentRunEvent events, closing after a terminal result event that carries the same summary, or an error event if the run fails; prefer streaming for long analyses. Pass chat_id to continue a saved conversation, or save=true to save the run as a new chat visible in the web UI; if saving fails, the answer is still returned but its chat_id is null. Tools that change data are available to the run only when the API key holds the write scope.

Requires an API key with the read scope.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.

promptstringRequired

streamfalseRequired

modelstring or nullOptional

chat_idstring or nullOptionalformat: "uuid"

savebooleanOptionalDefaults to false

Response

outputstring

modelstring

tool_callslist of objects

usageobject

chat_idstring or nullOptionalformat: "uuid"

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

422

Unprocessable Entity Error

500

Internal Server Error

502

Bad Gateway Error