Skip to content
POST/api/v1/autopilot/run

Manually trigger autopilot

Starts an autopilot audit for a project. Body requires `description` (1-2000 chars) and `depth` (quick | standard | deep) and `projectId`; `targetModel`, `complianceFrameworks` and `focusAreas` are optional. Reserves an eval usage unit (429 USAGE_LIMIT_EXCEEDED when the plan cap is hit) and 400 PROVIDER_ERROR when no provider key resolves for the model. Inserts an `eval_runs` row with status=running and returns 201 immediately with { runId, status, input, stages, estimatedTimeMs, estimatedCostUsd } — the six stages (understand, generate, eval, security, compliance, report) execute in the background and progress is polled from the eval-run row. Editor role; rate-limited to 3 runs per 5 minutes.

Authentication

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

Request body required

Example

{
  "description": "string",
  "targetModel": "string",
  "depth": "quick",
  "projectId": "00000000-0000-0000-0000-000000000000",
  "complianceFrameworks": [
    "string"
  ],
  "focusAreas": [
    "string"
  ]
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "description": {
          "type": "string",
          "minLength": 1,
          "maxLength": 2000
        },
        "targetModel": {
          "type": "string",
          "maxLength": 200
        },
        "depth": {
          "type": "string",
          "enum": [
            "quick",
            "standard",
            "deep"
          ]
        },
        "projectId": {
          "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)$"
        },
        "complianceFrameworks": {
          "maxItems": 20,
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 100
          }
        },
        "focusAreas": {
          "maxItems": 20,
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 100
          }
        }
      },
      "required": [
        "description",
        "depth",
        "projectId"
      ],
      "additionalProperties": false
    }
  }
}

Response

202 example

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

All status codes

201Created.
202Autopilot queued.
400(no description)
401(no description)
403Forbidden — insufficient role for this operation.
404Not Found — NOT_FOUND.
409Conflict — CONFLICT.
429(no description)
500Internal Server Error — DB_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/autopilot/run \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "description": "string", "targetModel": "string", "depth": "quick", "projectId": "00000000-0000-0000-0000-000000000000", "complianceFrameworks": [ "string" ], "focusAreas": [ "string" ] }'

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/autopilot/run", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "description": "string",
    "targetModel": "string",
    "depth": "quick",
    "projectId": "00000000-0000-0000-0000-000000000000",
    "complianceFrameworks": [
      "string"
    ],
    "focusAreas": [
      "string"
    ]
  }),
});
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/autopilot/run",
    headers=headers,
    json={
    "description": "string",
    "targetModel": "string",
    "depth": "quick",
    "projectId": "00000000-0000-0000-0000-000000000000",
    "complianceFrameworks": [
        "string"
    ],
    "focusAreas": [
        "string"
    ]
},
)
print(response.status_code, response.json())

Go

package main

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

func main() {
	body := strings.NewReader(`{"description":"string","targetModel":"string","depth":"quick","projectId":"00000000-0000-0000-0000-000000000000","complianceFrameworks":["string"],"focusAreas":["string"]}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/autopilot/run", 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

400401403404409429500

Other Evals endpoints