assistants

Create an assistant

Creates an assistant. Its knowledge mode chooses what it reads, one mode at a time: every workspace resource (all), chosen resource_ids (selected), or every resource carrying one of follow_tags (tags).

POST/v1/assistants

Request

curl --request POST \
  --url 'https://api.lookio.app/v1/assistants' \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
  "name": "<string>"
}'

import json
import requests

url = "https://api.lookio.app/v1/assistants"
headers = {
  "Authorization": "<api-key>",
  "Content-Type": "application/json"
}
payload = json.loads("{\"name\":\"<string>\"}")

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

const response = await fetch("https://api.lookio.app/v1/assistants", {
  method: "POST",
  headers: {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "name": "<string>"
  }),
});

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

<?php
$client = curl_init();

curl_setopt($client, CURLOPT_URL, "https://api.lookio.app/v1/assistants");
curl_setopt($client, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($client, CURLOPT_HTTPHEADER, [
    "Authorization: <api-key>",
    "Content-Type: application/json",
]);
curl_setopt($client, CURLOPT_POSTFIELDS, "{\"name\":\"<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.lookio.app/v1/assistants", bytes.NewBuffer([]byte("{\"name\":\"<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.lookio.app/v1/assistants"))
    .header("Authorization", "<api-key>")
    .header("Content-Type", "application/json")
    .method("POST", HttpRequest.BodyPublishers.ofString("{\"name\":\"<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.lookio.app/v1/assistants")
request = Net::HTTP::Post.new(uri)
request["Authorization"] = "<api-key>"
request["Content-Type"] = "application/json"
request.body = "{\"name\":\"<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": {
    "id": "ast_66xcnwtzj8vt",
    "name": "Support",
    "context": "You are the support assistant of Acme. You answer customers who want a quick, accurate reply.",
    "output_guidelines": "Short answers, in the language of the question.",
    "resource_ids": [
      "res_thk6smb5nvts"
    ],
    "follow_tags": [],
    "knowledge": "selected",
    "created_at": "2026-10-12T09:30:00.000Z",
    "updated_at": "2026-10-12T09:30:00.000Z"
  },
  "request_id": "req_01K9X7M2Q4"
}

{
  "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>"
}

{
  "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 assistants:write.

Creating an assistant is free. Asking it questions is not: see Ask an assistant.

knowledge decides what it reads: all, selected (the resource_ids) or tags (the follow_tags). When you omit it, Lookio infers tags if you sent only tags and selected otherwise. Send all to read every resource.

A resource id that does not exist fails with resource_not_found. An API key limited to specific assistants cannot create new ones and gets permission_denied.

Send an Idempotency-Key header so a retried request does not create two assistants. See Assistants.

Authorizations

Authorizationbearerin headerrequired

Header parameters

Idempotency-Keystringlength: 1–255 chars

A unique key for this request, such as a UUID, 1 to 255 visible ASCII characters. Send the same key when you retry: the first response is returned (with Idempotent-Replayed: true) instead of running the request again, for 24 hours, per credential. The same key on a different request is a 409 conflict. A streamed answer is not recorded.

Body

application/jsonrequired

namestringrequiredlength: 1–120 chars

contextstringdefault: ""length: ≤ 12000 chars

What the assistant is and who it talks to: its role and its audience.

output_guidelinesstringdefault: ""length: ≤ 12000 chars

How answers are written: length, format, language.

resource_idsstring[]default: []items: ≤ 200 items

The resources it answers from.

follow_tagsstring[]items: ≤ 30 items

Tags it follows when knowledge is tags: every resource carrying one, now or later, is used (one knowledge mode applies at a time).

knowledgeenum<string>one of: all, selected, tags

Omit to infer it: tags when only tags are given, otherwise selected. Send all to read every resource.

Response

application/json

Create an assistant

dataobjectrequired

Show child attributes

data.idstringrequiredpattern: ^ast_[abcdefghjkmnpqrstuvwxyz23456789]{12}$

data.namestringrequired

data.contextstringrequired

data.output_guidelinesstringrequired

data.resource_idsstring[]required

Empty when this caller may not see the resource catalogue.

data.follow_tagsstring[]required

data.knowledgeenum<string>requiredone of: all, selected, tags

What the assistant reads: all is every resource of the workspace, now and later; selected is only resource_ids; tags is every resource carrying a tag in follow_tags, now or later. One mode at a time; the lists of the other modes are kept.

data.created_atstringrequired

data.updated_atstringrequired

request_idstringrequired

{ "data": { "id": "ast_66xcnwtzj8vt", "name": "Support", "context": "You are the support assistant of Acme. You answer customers who want a quick, accurate reply.", "output_guidelines": "Short answers, in the language of the question.", "resource_ids": [ "res_thk6smb5nvts" ], "follow_tags": [], "knowledge": "selected", "created_at": "2026-10-12T09:30:00.000Z", "updated_at": "2026-10-12T09:30:00.000Z" }, "request_id": "req_01K9X7M2Q4" }

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

Create an assistant

Authorizations

Header parameters

Body

Response

Use these docs with your AI tools

Query these docs via MCP

Query these docs over HTTP

Read these docs as Markdown