feedback

Envoyer un retour sur l’agent

Enregistrez vos commentaires sur un résultat inattendu, un comportement déroutant, une erreur ou un aspect de l'API, du CLI ou du serveur MCP que vous souhaiteriez voir fonctionner différemment. Décrivez la situation, vos observations et le résultat attendu. Si possible, précisez l'outil, l'opération API ou la commande CLI concernée, le modèle d'IA et le harness d'agent utilisé. N'incluez pas de clés API, de jetons, d'URLs signées ou le contenu complet de fichiers. Cette action ne consomme pas de crédits et ne modifie pas votre espace de travail.

POST/v1/feedback

Request

curl --request POST \
  --url 'https://api.ai-glot.com/v1/feedback' \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
  "observed_problem": "<string>",
  "situation": "<string>",
  "expected_solution": "<string>"
}'

import json
import requests

url = "https://api.ai-glot.com/v1/feedback"
headers = {
  "Authorization": "<api-key>",
  "Content-Type": "application/json"
}
payload = json.loads("{\"observed_problem\":\"<string>\",\"situation\":\"<string>\",\"expected_solution\":\"<string>\"}")

response = requests.request("POST", url, headers=headers, json=payload)
print(response.json())

const response = await fetch("https://api.ai-glot.com/v1/feedback", {
  method: "POST",
  headers: {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "observed_problem": "<string>",
    "situation": "<string>",
    "expected_solution": "<string>"
  }),
});

const data = await response.json();
console.log(data);

<?php
$client = curl_init();

curl_setopt($client, CURLOPT_URL, "https://api.ai-glot.com/v1/feedback");
curl_setopt($client, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($client, CURLOPT_HTTPHEADER, [
    "Authorization: <api-key>",
    "Content-Type: application/json",
]);
curl_setopt($client, CURLOPT_POSTFIELDS, "{\"observed_problem\":\"<string>\",\"situation\":\"<string>\",\"expected_solution\":\"<string>\"}");
curl_setopt($client, CURLOPT_RETURNTRANSFER, true);

$response = curl_exec($client);
curl_close($client);
echo $response;

package main

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

func main() {
  req, _ := http.NewRequest("POST", "https://api.ai-glot.com/v1/feedback", bytes.NewBuffer([]byte("{\"observed_problem\":\"<string>\",\"situation\":\"<string>\",\"expected_solution\":\"<string>\"}")))
  req.Header.Set("Authorization", "<api-key>")
  req.Header.Set("Content-Type", "application/json")
  res, _ := http.DefaultClient.Do(req)
  defer res.Body.Close()
  data, _ := io.ReadAll(res.Body)
  fmt.Println(string(data))
}

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

var request = HttpRequest.newBuilder(URI.create("https://api.ai-glot.com/v1/feedback"))
    .header("Authorization", "<api-key>")
    .header("Content-Type", "application/json")
    .method("POST", HttpRequest.BodyPublishers.ofString("{\"observed_problem\":\"<string>\",\"situation\":\"<string>\",\"expected_solution\":\"<string>\"}"))
    .build();

var response = HttpClient.newHttpClient().send(
    request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI("https://api.ai-glot.com/v1/feedback")
request = Net::HTTP::Post.new(uri)
request["Authorization"] = "<api-key>"
request["Content-Type"] = "application/json"
request.body = "{\"observed_problem\":\"<string>\",\"situation\":\"<string>\",\"expected_solution\":\"<string>\"}"

response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: uri.scheme == "https") do |http|
  http.request(request)
end

puts response.body

application/json

{
  "data": {
    "feedback_id": "<string>",
    "received": true
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>"
  },
  "request_id": "<string>"
}

Utilisez cet endpoint lorsqu’un outil, une réponse, une erreur ou un flux de travail d’AI Glot ne se comporte pas comme prévu, ou lorsque vous aimeriez qu’une fonctionnalité fonctionne autrement.

La requête nécessite trois champs en texte libre :

JSON{
  "observed_problem": "The response did not explain why the translation was rejected.",
  "situation": "I called the MCP translation tool with a valid file and a clear instruction.",
  "expected_solution": "The tool should name the exact missing or invalid input."
}

Vous pouvez également inclure related_action (l’outil, l’endpoint ou la commande concernée), ai_model et agent_harness. Ces champs sont volontairement en texte libre : l’agent n’a pas à choisir dans un catalogue prédéfini.

L’endpoint utilise la même authentification par jeton Bearer que le reste de la plateforme développeur, sans portée supplémentaire. Il ne lit ni ne modifie les données de l’espace de travail et ne consomme aucun crédit. AI Glot transmet directement le retour sous forme d’événement structuré au webhook configuré du fondateur.

N’incluez pas de clés API, de jetons, d’URL signées ni le contenu intégral de fichiers.

Réponse

application/json

Envoyer un commentaire sur l'utilisation d'AI Glot

dataobjectrequired

Show child attributes

feedback_idstringrequired

receivedbooleanrequired

request_idstringrequired

curl --request POST \ --url 'https://api.ai-glot.com/v1/feedback' \ --header 'Authorization: <api-key>' \ --header 'Content-Type: application/json' \ --data '{ "observed_problem": "<string>", "situation": "<string>", "expected_solution": "<string>" }'

Envoyer un retour sur l’agent

Réponse

Use these docs with your AI tools

Query these docs via MCP

Query these docs over HTTP

Read these docs as Markdown