logs

List the answer logs

Every answer Lookio produced, one line each, whatever asked: a member in the chat, Lookio AI, an API key (REST, CLI, SDK), the MCP server, a widget's visitor. Latest first, with the assistant, who asked, the query mode, what it cost, how long it took, and the conversation it belongs to when it was kept. No question or answer text: read the conversation with GET /v1/logs/conversations/{conversation_id}. Filter by channel, assistant_id, widget_id, api_key_id, member_id, mode and from/to, and paginate with cursor. Members' own chats are visible to admins only, as lines without content, and never to an API key. Costs nothing.

GET/v1/logs/answers

Request

curl --request GET \
  --url 'https://api.lookio.app/v1/logs/answers' \
  --header 'Authorization: <api-key>'

import json
import requests

url = "https://api.lookio.app/v1/logs/answers"
headers = {
  "Authorization": "<api-key>"
}

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

const response = await fetch("https://api.lookio.app/v1/logs/answers", {
  method: "GET",
  headers: {
    "Authorization": "<api-key>"
  },
});

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

<?php
$client = curl_init();

curl_setopt($client, CURLOPT_URL, "https://api.lookio.app/v1/logs/answers");
curl_setopt($client, CURLOPT_CUSTOMREQUEST, "GET");
curl_setopt($client, CURLOPT_HTTPHEADER, [
    "Authorization: <api-key>",
]);
curl_setopt($client, CURLOPT_RETURNTRANSFER, true);

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

package main

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

func main() {
  req, _ := http.NewRequest("GET", "https://api.lookio.app/v1/logs/answers", nil)
  req.Header.Set("Authorization", "<api-key>")
  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.lookio.app/v1/logs/answers"))
    .header("Authorization", "<api-key>")
    .method("GET", HttpRequest.BodyPublishers.noBody())
    .build();

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

require 'net/http'
require 'json'

uri = URI("https://api.lookio.app/v1/logs/answers")
request = Net::HTTP::Get.new(uri)
request["Authorization"] = "<api-key>"

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": [
    {
      "id": "<string>",
      "channel": "chat",
      "assistant": {
        "id": "<string>",
        "name": null
      },
      "member": {
        "id": "<string>",
        "name": null
      },
      "api_key": {
        "id": "<string>",
        "name": null
      },
      "widget": {
        "id": "<string>",
        "name": "<string>"
      },
      "end_user": null,
      "mode": "<string>",
      "credits": 123,
      "duration_ms": 123,
      "conversation_id": null,
      "created_at": "<string>"
    }
  ],
  "has_more": true,
  "next_cursor": null,
  "limit": 123,
  "request_id": "<string>"
}

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

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

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

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

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

Requires usage:read.

One line per answer, whatever asked: a member in the app’s chat (chat), Lookio AI (lookio_ai), an API key through REST, the CLI or the SDK (api), the MCP server (mcp) or the visitor of a widget (widget). Results come latest first, and you page with cursor, an opaque string: pass next_cursor back unchanged. See Pagination.

A line holds metadata only: the assistant, who asked, the query mode, the model, the tokens, the credits it cost, how long it took, and whether the resources held an answer (answered is false for a free no-answer). It never holds the question or the answer. When the exchange was kept, conversation_id leads to it: read it with Retrieve a logged conversation, which needs assistants:write. An answer sent with store: false has no conversation, and shows as api.

Narrow the list with channel (comma-separated), assistant_id, widget_id, api_key_id, member_id, result (answered or no_answer), mode and from and to. result=no_answer finds the questions your resources could not answer.

A member’s own chats appear to admins only, as lines without content, and never to an API key. See Logs. The figures over the same filters are in Retrieve the figures of the answer logs.

Authorizations

Authorizationbearerin headerrequired

Query parameters

channelstringlength: ≥ 1 chars

Only the answers from these channels, comma-separated: chat (a member in the app's chat), lookio_ai (the in-app agent), api (an API key through REST, the CLI or the SDK), mcp (the MCP server), widget (a visitor of a widget). Default: all.

assistant_idstringpattern: ^ast_[abcdefghjkmnpqrstuvwxyz23456789]{12}$

Only the answers of this assistant.

widget_idstringpattern: ^wdg_[abcdefghjkmnpqrstuvwxyz23456789]{12}$

Only this widget's answers.

api_key_idstringlength: 1–64 chars

Only the answers asked with this API key.

member_idstringlength: 1–64 chars

Only this member's answers (admins).

modestringlength: 1–40 chars

Only this query mode (flash, fast, deep…).

fromstring

Only answers since this ISO 8601 date or timestamp.

tostring

Only answers until this ISO 8601 date or timestamp.

cursorstringlength: 1–200 chars

Pass next_cursor from the previous page, unchanged.

limitintegerrange: 1–100

Number of items to return. Values outside 1-100 are clamped, and the response reports the limit actually applied.

Response

application/json

List the answer logs

dataobject[]required

Show child attributes

data.idstringrequired

The answer's request id.

data.channelenum<string>requiredone of: chat, lookio_ai, api, mcp, widget

Where the question came from: chat, lookio_ai, api, mcp or widget. An API key's answer kept nowhere (store: false) shows as api.

data.assistantobject | nullrequired

Null for Lookio AI, which answers about the workspace itself.

Show child attributes

data.assistant.idstringrequired

data.assistant.namestringnullrequired

data.memberobject | nullrequired

The member who asked, for chat and lookio_ai.

Show child attributes

data.member.idstringrequired

data.member.namestringnullrequired

data.api_keyobject | nullrequired

The API key that asked.

Show child attributes

data.api_key.idstringrequired

data.api_key.namestringnullrequired

data.widgetobject | nullrequired

The widget whose visitor asked.

Show child attributes

data.widget.idstringrequired

data.widget.namestringrequired

data.end_userstringnullrequired

The widget visitor's id, or the end_user your product sent.

data.modestringrequired

The query mode, or agent-<model> for Lookio AI.

data.creditsintegerrequired

What the answer cost.

data.duration_msinteger | nullrequired

How long it took, when the answer was kept.

data.conversation_idstringnullrequired

The conversation of a widget, API or MCP answer that was kept: read it with GET /v1/logs/conversations/{conversation_id}.

data.created_atstringrequired

has_morebooleanrequired

True when another page follows: pass next_cursor back as cursor.

next_cursorstringnullrequired

Pass it back unchanged as cursor. Null on the last page.

limitintegerrequired

The page size actually applied.

request_idstringrequired

List the answer logs

Authorizations

Query parameters

Response

Use these docs with your AI tools

Query these docs via MCP

Query these docs over HTTP

Read these docs as Markdown