Execute Evaluation

curl --request POST \
  --url https://api.example.com/eval-runs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "agent_id": "<string>",
  "team_id": "<string>",
  "model_id": "<string>",
  "model_provider": "<string>",
  "additional_guidelines": "<string>",
  "additional_context": "<string>",
  "num_iterations": 1,
  "name": "<string>",
  "expected_output": "<string>",
  "criteria": "<string>",
  "scoring_strategy": "binary",
  "threshold": 7,
  "warmup_runs": 0,
  "expected_tool_calls": [
    "<string>"
  ]
}
'

import requests

url = "https://api.example.com/eval-runs"

payload = {
    "input": "<string>",
    "agent_id": "<string>",
    "team_id": "<string>",
    "model_id": "<string>",
    "model_provider": "<string>",
    "additional_guidelines": "<string>",
    "additional_context": "<string>",
    "num_iterations": 1,
    "name": "<string>",
    "expected_output": "<string>",
    "criteria": "<string>",
    "scoring_strategy": "binary",
    "threshold": 7,
    "warmup_runs": 0,
    "expected_tool_calls": ["<string>"]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    input: '<string>',
    agent_id: '<string>',
    team_id: '<string>',
    model_id: '<string>',
    model_provider: '<string>',
    additional_guidelines: '<string>',
    additional_context: '<string>',
    num_iterations: 1,
    name: '<string>',
    expected_output: '<string>',
    criteria: '<string>',
    scoring_strategy: 'binary',
    threshold: 7,
    warmup_runs: 0,
    expected_tool_calls: ['<string>']
  })
};

fetch('https://api.example.com/eval-runs', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/eval-runs",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'input' => '<string>',
    'agent_id' => '<string>',
    'team_id' => '<string>',
    'model_id' => '<string>',
    'model_provider' => '<string>',
    'additional_guidelines' => '<string>',
    'additional_context' => '<string>',
    'num_iterations' => 1,
    'name' => '<string>',
    'expected_output' => '<string>',
    'criteria' => '<string>',
    'scoring_strategy' => 'binary',
    'threshold' => 7,
    'warmup_runs' => 0,
    'expected_tool_calls' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/eval-runs"

	payload := strings.NewReader("{\n  \"input\": \"<string>\",\n  \"agent_id\": \"<string>\",\n  \"team_id\": \"<string>\",\n  \"model_id\": \"<string>\",\n  \"model_provider\": \"<string>\",\n  \"additional_guidelines\": \"<string>\",\n  \"additional_context\": \"<string>\",\n  \"num_iterations\": 1,\n  \"name\": \"<string>\",\n  \"expected_output\": \"<string>\",\n  \"criteria\": \"<string>\",\n  \"scoring_strategy\": \"binary\",\n  \"threshold\": 7,\n  \"warmup_runs\": 0,\n  \"expected_tool_calls\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/eval-runs")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"<string>\",\n  \"agent_id\": \"<string>\",\n  \"team_id\": \"<string>\",\n  \"model_id\": \"<string>\",\n  \"model_provider\": \"<string>\",\n  \"additional_guidelines\": \"<string>\",\n  \"additional_context\": \"<string>\",\n  \"num_iterations\": 1,\n  \"name\": \"<string>\",\n  \"expected_output\": \"<string>\",\n  \"criteria\": \"<string>\",\n  \"scoring_strategy\": \"binary\",\n  \"threshold\": 7,\n  \"warmup_runs\": 0,\n  \"expected_tool_calls\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/eval-runs")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"input\": \"<string>\",\n  \"agent_id\": \"<string>\",\n  \"team_id\": \"<string>\",\n  \"model_id\": \"<string>\",\n  \"model_provider\": \"<string>\",\n  \"additional_guidelines\": \"<string>\",\n  \"additional_context\": \"<string>\",\n  \"num_iterations\": 1,\n  \"name\": \"<string>\",\n  \"expected_output\": \"<string>\",\n  \"criteria\": \"<string>\",\n  \"scoring_strategy\": \"binary\",\n  \"threshold\": 7,\n  \"warmup_runs\": 0,\n  \"expected_tool_calls\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "id": "f2b2d72f-e9e2-4f0e-8810-0a7e1ff58614",
  "agent_id": "basic-agent",
  "model_id": "gpt-4o",
  "model_provider": "OpenAI",
  "eval_type": "reliability",
  "eval_data": {
    "eval_status": "PASSED",
    "failed_tool_calls": [],
    "passed_tool_calls": [
      "multiply"
    ]
  },
  "created_at": "2025-08-27T15:41:59Z",
  "updated_at": "2025-08-27T15:41:59Z"
}

{
  "detail": "Bad request",
  "error_code": "BAD_REQUEST"
}

{
  "detail": "Unauthenticated access",
  "error_code": "UNAUTHENTICATED"
}

{
  "detail": "Not found",
  "error_code": "NOT_FOUND"
}

{
  "detail": "Validation error",
  "error_code": "VALIDATION_ERROR"
}

{
  "detail": "Internal server error",
  "error_code": "INTERNAL_SERVER_ERROR"
}

POST

eval-runs

Execute Evaluation

curl --request POST \
  --url https://api.example.com/eval-runs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "agent_id": "<string>",
  "team_id": "<string>",
  "model_id": "<string>",
  "model_provider": "<string>",
  "additional_guidelines": "<string>",
  "additional_context": "<string>",
  "num_iterations": 1,
  "name": "<string>",
  "expected_output": "<string>",
  "criteria": "<string>",
  "scoring_strategy": "binary",
  "threshold": 7,
  "warmup_runs": 0,
  "expected_tool_calls": [
    "<string>"
  ]
}
'

import requests

url = "https://api.example.com/eval-runs"

payload = {
    "input": "<string>",
    "agent_id": "<string>",
    "team_id": "<string>",
    "model_id": "<string>",
    "model_provider": "<string>",
    "additional_guidelines": "<string>",
    "additional_context": "<string>",
    "num_iterations": 1,
    "name": "<string>",
    "expected_output": "<string>",
    "criteria": "<string>",
    "scoring_strategy": "binary",
    "threshold": 7,
    "warmup_runs": 0,
    "expected_tool_calls": ["<string>"]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    input: '<string>',
    agent_id: '<string>',
    team_id: '<string>',
    model_id: '<string>',
    model_provider: '<string>',
    additional_guidelines: '<string>',
    additional_context: '<string>',
    num_iterations: 1,
    name: '<string>',
    expected_output: '<string>',
    criteria: '<string>',
    scoring_strategy: 'binary',
    threshold: 7,
    warmup_runs: 0,
    expected_tool_calls: ['<string>']
  })
};

fetch('https://api.example.com/eval-runs', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/eval-runs",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'input' => '<string>',
    'agent_id' => '<string>',
    'team_id' => '<string>',
    'model_id' => '<string>',
    'model_provider' => '<string>',
    'additional_guidelines' => '<string>',
    'additional_context' => '<string>',
    'num_iterations' => 1,
    'name' => '<string>',
    'expected_output' => '<string>',
    'criteria' => '<string>',
    'scoring_strategy' => 'binary',
    'threshold' => 7,
    'warmup_runs' => 0,
    'expected_tool_calls' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/eval-runs"

	payload := strings.NewReader("{\n  \"input\": \"<string>\",\n  \"agent_id\": \"<string>\",\n  \"team_id\": \"<string>\",\n  \"model_id\": \"<string>\",\n  \"model_provider\": \"<string>\",\n  \"additional_guidelines\": \"<string>\",\n  \"additional_context\": \"<string>\",\n  \"num_iterations\": 1,\n  \"name\": \"<string>\",\n  \"expected_output\": \"<string>\",\n  \"criteria\": \"<string>\",\n  \"scoring_strategy\": \"binary\",\n  \"threshold\": 7,\n  \"warmup_runs\": 0,\n  \"expected_tool_calls\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/eval-runs")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"<string>\",\n  \"agent_id\": \"<string>\",\n  \"team_id\": \"<string>\",\n  \"model_id\": \"<string>\",\n  \"model_provider\": \"<string>\",\n  \"additional_guidelines\": \"<string>\",\n  \"additional_context\": \"<string>\",\n  \"num_iterations\": 1,\n  \"name\": \"<string>\",\n  \"expected_output\": \"<string>\",\n  \"criteria\": \"<string>\",\n  \"scoring_strategy\": \"binary\",\n  \"threshold\": 7,\n  \"warmup_runs\": 0,\n  \"expected_tool_calls\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/eval-runs")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"input\": \"<string>\",\n  \"agent_id\": \"<string>\",\n  \"team_id\": \"<string>\",\n  \"model_id\": \"<string>\",\n  \"model_provider\": \"<string>\",\n  \"additional_guidelines\": \"<string>\",\n  \"additional_context\": \"<string>\",\n  \"num_iterations\": 1,\n  \"name\": \"<string>\",\n  \"expected_output\": \"<string>\",\n  \"criteria\": \"<string>\",\n  \"scoring_strategy\": \"binary\",\n  \"threshold\": 7,\n  \"warmup_runs\": 0,\n  \"expected_tool_calls\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "id": "f2b2d72f-e9e2-4f0e-8810-0a7e1ff58614",
  "agent_id": "basic-agent",
  "model_id": "gpt-4o",
  "model_provider": "OpenAI",
  "eval_type": "reliability",
  "eval_data": {
    "eval_status": "PASSED",
    "failed_tool_calls": [],
    "passed_tool_calls": [
      "multiply"
    ]
  },
  "created_at": "2025-08-27T15:41:59Z",
  "updated_at": "2025-08-27T15:41:59Z"
}

{
  "detail": "Bad request",
  "error_code": "BAD_REQUEST"
}

{
  "detail": "Unauthenticated access",
  "error_code": "UNAUTHENTICATED"
}

{
  "detail": "Not found",
  "error_code": "NOT_FOUND"
}

{
  "detail": "Validation error",
  "error_code": "VALIDATION_ERROR"
}

{
  "detail": "Internal server error",
  "error_code": "INTERNAL_SERVER_ERROR"
}

Authorizations

Authorization

string

header

required

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

Query Parameters

db_id

string | null

Database ID to use for evaluation

table

string | null

Table to use for evaluation

Body

application/json

eval_type

enum<string>

required

Type of evaluation to run (accuracy, performance, or reliability)

Available options:

accuracy,

agent_as_judge,

performance,

reliability

input

string

required

Input text/query for the evaluation

Minimum string length: 1

agent_id

string | null

Agent ID to evaluate

team_id

string | null

Team ID to evaluate

model_id

string | null

Model ID to use for evaluation

model_provider

string | null

Model provider name

additional_guidelines

string | null

Additional guidelines for the evaluation

additional_context

string | null

Additional context for the evaluation

num_iterations

integer

default:1

Number of times to run the evaluation

Required range: 1 <= x <= 100

name

string | null

Name for this evaluation run

expected_output

string | null

Expected output for accuracy evaluation

criteria

string | null

Evaluation criteria for agent-as-judge evaluation

scoring_strategy

enum<string> | null

default:binary

Scoring strategy: 'numeric' (1-10 with threshold) or 'binary' (PASS/FAIL)

Available options:

numeric,

binary

threshold

integer | null

default:7

Score threshold for pass/fail (1-10), only used with numeric scoring

Required range: 1 <= x <= 10

warmup_runs

integer

default:0

Number of warmup runs before measuring performance

Required range: 0 <= x <= 10

expected_tool_calls

string[] | null

Expected tool calls for reliability evaluation

Response

Evaluation executed successfully

string

required

Unique identifier for the evaluation run

eval_type

enum<string>

required

Type of evaluation (accuracy, performance, or reliability)

Available options:

accuracy,

agent_as_judge,

performance,

reliability

eval_data

Eval Data · object

required

Evaluation results and metrics

agent_id

string | null

Agent ID that was evaluated

model_id

string | null

Model ID used in evaluation

model_provider

string | null

Model provider name

team_id

string | null

Team ID that was evaluated

workflow_id

string | null

Workflow ID that was evaluated

name

string | null

Name of the evaluation run

evaluated_component_name

string | null

Name of the evaluated component

eval_input

Eval Input · object | null

Input parameters used for the evaluation

created_at

string<date-time> | null

Timestamp when evaluation was created

updated_at

string<date-time> | null

Timestamp when evaluation was last updated

List Evaluation Runs Delete Evaluation Runs

⌘I