Ship reliable, testable agents – not guesses. Better Agents adds simulations, evaluations, and standards on top of any framework. Explore Better Agents
import requests
url = "https://app.langwatch.ai/api/evaluators"
payload = {
"name": "<string>",
"config": {}
}
headers = {
"X-Auth-Token": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"id": "<string>",
"projectId": "<string>",
"name": "<string>",
"slug": "<string>",
"type": "<string>",
"config": {},
"workflowId": "<string>",
"copiedFromEvaluatorId": "<string>",
"createdAt": "<string>",
"updatedAt": "<string>",
"fields": [
{
"identifier": "<string>",
"type": "<string>",
"optional": true
}
],
"outputFields": [
{
"identifier": "<string>",
"type": "<string>",
"optional": true
}
],
"workflowName": "<string>",
"workflowIcon": "<string>"
}Create a new evaluator
import requests
url = "https://app.langwatch.ai/api/evaluators"
payload = {
"name": "<string>",
"config": {}
}
headers = {
"X-Auth-Token": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"id": "<string>",
"projectId": "<string>",
"name": "<string>",
"slug": "<string>",
"type": "<string>",
"config": {},
"workflowId": "<string>",
"copiedFromEvaluatorId": "<string>",
"createdAt": "<string>",
"updatedAt": "<string>",
"fields": [
{
"identifier": "<string>",
"type": "<string>",
"optional": true
}
],
"outputFields": [
{
"identifier": "<string>",
"type": "<string>",
"optional": true
}
],
"workflowName": "<string>",
"workflowIcon": "<string>"
}Success
Show child attributes
Show child attributes
Show child attributes
Was this page helpful?