Skip to content
POST/api/v1/insights/agent/generate

Generate agent insights

Generates an LLM insights report SYNCHRONOUSLY and returns it in the 201 body — no polling required. Body: projectId (uuid, required), windowDays (clamped 1-90, default 7), k (clamped 3-12, default 6). Pulls up to 5000 agent_steps with a 2-D embedding in the window (joined through agent_traces for project scope), k-means clusters them, and hands the cluster summary plus samples to gpt-4o-mini for top failure modes / cost+latency outliers / anomalies / recommended actions. Fewer than 30 embedded steps returns 400 NOT_ENOUGH_DATA. Response: { reportId, status: 'completed', summary, findings {topClusters, anomalyCount, anomalySampleIds}, stats {traceCount, clusterCount, anomalyCount, generationMs, costUsd} }. The row is persisted to insight_reports (in_progress → completed/failed) and is retrievable afterwards via GET /api/v1/insights/agent/reports. Rate-limited to 6/min. Audit-logged.

Authentication

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

Request body required

Example

{
  "projectId": "00000000-0000-0000-0000-000000000000",
  "windowDays": 0,
  "k": 0
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "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)$"
        },
        "windowDays": {
          "type": "number"
        },
        "k": {
          "type": "number"
        }
      },
      "required": [
        "projectId"
      ],
      "additionalProperties": {}
    }
  }
}

Response

202 example

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

All status codes

201Created.
202Generation queued.
400(no description)
401(no description)
403Forbidden — insufficient role for this operation.
404Not Found — NOT_FOUND.
429(no description)
500Internal Server Error — DB_ERROR, GENERATION_FAILED, NO_LLM_KEY.
502Bad Gateway — LLM_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/insights/agent/generate \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "projectId": "00000000-0000-0000-0000-000000000000", "windowDays": 0, "k": 0 }'

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/insights/agent/generate", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "projectId": "00000000-0000-0000-0000-000000000000",
    "windowDays": 0,
    "k": 0
  }),
});
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/insights/agent/generate",
    headers=headers,
    json={
    "projectId": "00000000-0000-0000-0000-000000000000",
    "windowDays": 0,
    "k": 0
},
)
print(response.status_code, response.json())

Go

package main

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

func main() {
	body := strings.NewReader(`{"projectId":"00000000-0000-0000-0000-000000000000","windowDays":0,"k":0}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/insights/agent/generate", 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

400401403404429500502

Other Monitoring endpoints