Skip to content
POST/api/v1/auto-eval

Trigger auto-eval pipeline

Evaluates ONE stored agent trace for quality issues. Body: { traceId } (uuid, required) — a `rules` field is rejected with 400 UNSUPPORTED_PARAMETER because an auto-eval rule needs a `check` function that JSON cannot express, so the built-in rule set always runs. Loads the trace plus its first 500 steps (org resolved from the trace's project and membership-verified before the handler runs; `evals:create`), runs the deterministic rule-based `autoEvalTrace` evaluator (pure functions — no LLM judge) and answers INLINE, synchronously: { traceId, findings, score, summary, spanCount, totalLatency }. 404 if the trace does not exist. Rate limit 30/min.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Request body required

Example

{
  "traceId": "00000000-0000-0000-0000-000000000000"
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "traceId": {
          "type": "string",
          "format": "uuid",
          "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
        },
        "rules": {}
      },
      "required": [
        "traceId"
      ],
      "additionalProperties": false
    }
  }
}

Response

202 example

{
  "job_id": "00000000-0000-0000-0000-000000000000"
}

All status codes

200OK.
202Auto-eval queued.
400(no description)
401(no description)
403Forbidden — insufficient role for this operation.
404Not Found — NOT_FOUND.
429(no description)
500Internal Server Error — AUTO_EVAL_ERROR, DB_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/auto-eval \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "traceId": "00000000-0000-0000-0000-000000000000" }'

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/auto-eval", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "traceId": "00000000-0000-0000-0000-000000000000"
  }),
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}
headers["Content-Type"] = "application/json"

response = requests.request(
    "POST",
    "https://evalguard.ai/api/v1/auto-eval",
    headers=headers,
    json={
    "traceId": "00000000-0000-0000-0000-000000000000"
},
)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"traceId":"00000000-0000-0000-0000-000000000000"}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/auto-eval", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403404429500

Other Evals endpoints