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

Eval-assistant — NL → eval config

Takes a natural-language description of what to test and returns heuristically-suggested scorers — a non-LLM, keyword-driven match. Body: { description (10-20,000 chars, required), industry?, sampleInputs? (max 200, each ≤20,000 chars) }. Returns the suggested scorers (name/type/weight/rationale), the industry-specific scorer list when `industry` is supplied, a truncated echo of the description, the count of sample inputs received, and a human-readable message. It does NOT generate test cases, pick a target model, or produce a runnable eval config; `sampleInputs` is counted but not otherwise used.

Authentication

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

Request body required

Example

{
  "description": "string",
  "industry": "string",
  "sampleInputs": [
    "string"
  ]
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "description": {
          "type": "string",
          "minLength": 10,
          "maxLength": 20000
        },
        "industry": {
          "type": "string",
          "maxLength": 120
        },
        "sampleInputs": {
          "maxItems": 200,
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 20000
          }
        }
      },
      "required": [
        "description"
      ],
      "additionalProperties": false
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Synthesized eval config.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
429(no description)
500Internal Server Error — an unhandled error was converted to the standard error envelope (INTERNAL_ERROR).

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/eval-assistant \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "description": "string", "industry": "string", "sampleInputs": [ "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/eval-assistant", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "description": "string",
    "industry": "string",
    "sampleInputs": [
      "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/eval-assistant",
    headers=headers,
    json={
    "description": "string",
    "industry": "string",
    "sampleInputs": [
        "string"
    ]
},
)
print(response.status_code, response.json())

Go

package main

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

func main() {
	body := strings.NewReader(`{"description":"string","industry":"string","sampleInputs":["string"]}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/eval-assistant", 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

400401403429500

Other NL Pipeline endpoints