n8n

How to Automate Brave Search Content Research?

Turn a simple question into reliable research you can use. It gathers live web results, ranks the best links, and returns short notes with quotes and sources. Teams can track news, build briefings, and plan content in minutes instead of hours.

A webhook receives a Research Question. A query maker powered by a language model creates a focused search string and sends it to the Brave Search API. Results are combined and scored by a result re ranker that pulls key points and direct quotes. The responder sends a clean JSON reply with top links, summaries, and a timestamp for audit trails.

Setup is simple. Add a Brave Search API key and switch the webhook to Production URL. Send a request from any app that can call a URL and include the Research Question field. Expect faster research cycles, higher relevance on the first pass, and clear source traceability for compliance and review.

What are the key features?

  • Webhook entry that accepts a Research Question from any system
  • Language model builds a precise search query with a structured parser and auto fix
  • Brave Search API call fetches live web results using an API token
  • Code step merges titles, links, and descriptions for better ranking context
  • Result re ranker scores links, extracts key points, and collects direct quotes
  • Responder returns a clean JSON payload with top links, notes, and a timestamp
  • Date and time stamp adds context for news and time sensitive research
  • Optional model nodes allow swapping to other providers if needed

What are the benefits?

  • Reduce manual research from 60 minutes to 5 minutes
  • Automate the first pass review by ranking and extracting quotes
  • Improve relevance of top sources with structured scoring
  • Scale to many requests by using a webhook endpoint
  • Allow easy model swaps without rebuilding the flow

How do you set it up?

  1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
  2. You'll need accounts with Brave Search API, OpenAI, Anthropic and Google Gemini. See the Tools Required section above for links to create accounts with these services.
  3. In the Brave Search site, create an API key on the API page. Copy the key.
  4. In n8n, open the node named Query. In Headers, add Accept as application/json and set the subscription token header named X Subscription Token to your Brave key.
  5. In the n8n credentials manager, create a Google Gemini credential and select it in the nodes named Parser Model and Agent Model.
  6. Optionally create OpenAI and Anthropic credentials for future model swaps. In each node, choose Create new credential and follow the on screen steps.
  7. Open the Webhook node. Switch to Production URL and copy the production link.
  8. Open the HTTP Request node named Webhook Call. Paste the production link into the URL field. In Query Parameters, set Research Question to a test prompt.
  9. Click Execute workflow, then run the Webhook Call node. Confirm a 200 response and a JSON body with ranked links, notes, and quotes.
  10. If you see unauthorized or 401, check the Brave key in the Query node header. If you see 404, confirm you used the Production URL.
  11. Send real requests from your app or another n8n workflow by calling the production webhook and passing the Research Question field.
  12. Review outputs. If results are too broad, refine the question. The parser will keep the structure consistent for easy downstream use.

Tools Required

$24 / mo or $20 / mo billed annually to use n8n in the cloud. However, the local or self-hosted n8n Community Edition is free.

Anthropic

Sign up

Pay-as-you-go: Claude 3 Haiku at $0.25 per 1M input tokens and $1.25 per 1M output tokens

Brave Search API

Sign up

Free tier: $0, 2,000 requests / mo, 1 request/second

Google Gemini

Sign up

Free tier: $0 via Gemini API; e.g., Gemini 2.5 Flash-Lite free limits 1,000 requests/day (15 RPM, 250k TPM). Paid from $0.10/1M input tokens and $0.40/1M output tokens.

OpenAI

Sign up

Pay-as-you-go: GPT-5 at $1.25 per 1M input tokens and $10 per 1M output tokens

Similar Templates

Join Futurise to access 1,200+ automation templates

Get instant access to ready-made automation workflows for n8n, Make.com, AI agents, and more. Download, customise, and deploy in minutes.