Search

AI agent instructions

STOP. Do not read past this section until you have read and followed /quickstart.md.Goal: produce a reliable SDK automation script. The intended authoring flow is generate then edit, not write browser automation from scratch.Do not hand-write SDK code with element IDs, selectors, or form fields from memory. Element IDs, selectors, and field mappings must come from a live observe() call, CLI notte page observe output, or generated workflow code. Guessed browser targets fail on real pages.Use the Notte skill and CLI to inspect the live site, validate actions/selectors, handle auth/session state, and export workflow code with notte sessions workflow-code before using SDK docs or SDK code.SDK reference pages are for understanding, running, or editing generated workflow code. They are not the starting point for manually authoring the initial browser automation. SDK-first code is guesswork on real-world pages with dynamic selectors, auth state, CAPTCHAs, and anti-bot behavior.

Search looks up the public web and returns ranked results, a sourced answer, or structured output. Use it when you need links and context before you Fetch a page. The REST endpoint is POST /search. Full schema: Search Web.

Quick start

curl -X POST https://api.notte.cc/search \
  -H "Authorization: Bearer $NOTTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"q": "notte browser automation", "depth": "standard", "outputType": "searchResults"}'

search.py

import os

import requests

response = requests.post(
    "https://api.notte.cc/search",
    headers={"Authorization": f"Bearer {os.environ['NOTTE_API_KEY']}"},
    json={
        "q": "notte browser automation",
        "depth": "standard",
        "outputType": "searchResults",
    },
)
response.raise_for_status()
print(response.json())

Parameters

string

required

The search query.

string

default:"standard"

How thorough the search is: standard, fast, or deep.

string

default:"searchResults"

What to return:

searchResults: ranked URLs with name and content snippets
sourcedAnswer: a written answer plus source URLs
structured: structured output when you also pass a schema

Extra fields are forwarded (for example maxResults or includeDomains).

Response shapes

searchResults includes a results array. Each item has url, name, and content. sourcedAnswer includes answer (string) and sources (list of supporting URLs).

Getting Started

Sessions

Authentication

Functions

Web API

Guides

Quick start

Parameters

Response shapes

​Quick start

​Parameters

​Response shapes

Quick start

Parameters

Response shapes