Turn a chat question into a clear research report. Built for marketing and content teams that need fast topic research, competitor notes, or source-backed briefs without jumping across tabs.

A chat message starts the flow. An AI model on OpenRouter turns the question into up to four focused search queries. Code steps parse that text and split it into batches. The system calls SerpAPI to get top results, formats the organic links, and then uses Jina AI to read each page in clean text. An AI agent extracts only the relevant facts, keeps short term memory for context, and can pull extra details from Wikipedia. A final AI step writes a structured report that ties everything back to the original question.

You will need API keys for OpenRouter, SerpAPI, and Jina AI added as n8n credentials. After setup, teams can cut research time from hours to minutes and handle more topics each week with steady quality. Great for content briefs, market snapshots, product research, and FAQ drafts that need clear sources and consistent structure.

• Chat message trigger collects the user question and starts the run
• OpenRouter LLM generates up to four precise search queries from the prompt
• Code nodes parse the LLM output and prepare clean batches
• SerpAPI search pulls organic results from Google for each query
• Result formatter extracts useful fields from the SerpAPI response
• Jina AI fetches readable page text for each URL to avoid clutter
• LLM agent extracts only the relevant context and keeps session memory
• Wikipedia tool adds helpful background facts when needed
• Final LLM composes a well structured research report
• Split in Batches nodes control rate limits and process large lists safely

• Reduce manual research from 2 hours to 10 minutes per topic
• Automate about 80 percent of source discovery and reading
• Improve report consistency by using one structured flow
• Handle 5 times more topics per week with the same team
• Connect SerpAPI, Jina AI, OpenRouter and Wikipedia in one place

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 OpenRouter, SerpAPI, Jina AI and Wikipedia. See the Tools Required section above for links to create accounts with these services.
3. In the n8n credentials manager, create an OpenRouter credential using your API key from your OpenRouter account. Double click the LLM model node and select this credential in the Credential to connect with field.
4. Create a SerpAPI credential with your API key from the SerpAPI dashboard. Open the SerpAPI HTTP Request node and pick this credential so the q and engine parameters work.
5. Create a Jina AI HTTP Header credential using your token from the Jina AI key manager. Open the Jina AI HTTP Request node and select this credential to authorize content fetches.
6. No credential is needed for Wikipedia. The tool node works out of the box. Ensure it stays connected to the final report step.
7. Open the Chat Message Trigger node and note the Webhook ID. Use the n8n chat interface to send test questions during validation.
8. Review the Code nodes. Confirm they parse LLM output and format SerpAPI results as expected. Keep keys and URLs out of plain text.
9. Check the Split in Batches nodes. Adjust batch size if you hit rate limits or need faster runs.
10. Run a test with a simple topic. Confirm SerpAPI returns results, Jina AI fetches page text, and the final report is created.
11. If SerpAPI returns no results, try a broader query or verify your API key and daily limits in SerpAPI.
12. If Jina AI returns an error, confirm the token is valid and the URL is reachable. For OpenRouter errors, verify the model name and that your account has credits.
13. Enable the workflow, then use the chat interface to submit real questions. Monitor the execution logs for any failed items and adjust batch sizes or prompts as needed.