An n8n workflow turns a topic into up to three Tavily searches, compiles a Markdown report with an agent, and pushes it to a Notion page.
An n8n workflow turns a topic into up to three Tavily searches, compiles a Markdown report with an agent, and pushes it to a Notion page.
A webhook passes the user's topic to a Strategy Agent, which asks 2–3 clarifying questions and then creates a Notion database page. The workflow generates up to three search queries. For each one, Tavily finds the top link and extracts its content. A Final Report Agent writes a Markdown report from the combined content. Gemini converts it to HTML in chunks, and the chunks are pushed into the Notion page.
The workflow returns the Notion report link to the user with no manual steps after the clarifying questions. The source gives no quality, speed or cost figures. Each query uses only its single top-ranked source.
You need keys for Tavily, Notion, an OpenRouter or OpenAI model, and Google Gemini, plus a Notion database ID connected in n8n.
Build an n8n workflow that takes a research topic [topic] and runs up to three web searches with Tavily. An AI agent should then compile the findings into a Markdown report with headings, key findings and source links, and save it as a new page in my Notion [parent page or database]. You're done when one test topic produces a finished Notion page; confirm the Notion destination with me before it writes anything.
Score every demo request against your ICP, update HubSpot and ping the right rep in Slack within a minute of the form submit.
Every new Zendesk ticket gets a category, priority and sentiment tag plus a draft reply in an internal note before an agent opens it.
Each month, find posts whose search clicks dropped, research what changed with Perplexity, and get a Claude-written refresh brief for each one.