Give your team a chat assistant that answers questions from your Notion knowledge base. It is ideal for support and operations teams that need fast, accurate answers without digging through pages.

A chat message triggers an AI Agent powered by the OpenAI Chat Model. The agent keeps a short memory window for context and uses two Notion tools. First it gets database details to learn the latest tags. Then it searches the Notion database by keyword or tag and pulls page content from the selected record. A Set node passes session data and tag options to guide the agent. The result is a clear answer drawn from one source of truth in Notion.

To set it up you need a Notion integration with access to your knowledge base and an OpenAI API key. Map both credentials in n8n, select your database in the Notion node, and test using the Chat URL. Teams can expect faster replies to common questions, fewer repeated pings to subject experts, and quicker onboarding. Use it for internal help desks, policy lookups, product facts, and standard operating procedures.

• Chat trigger starts whenever a user sends a message.
• OpenAI Chat Model generates clear answers based on Notion content.
• AI Agent decides when to use Notion search and page fetch tools.
• Window Buffer Memory keeps the last 4 messages for context.
• Notion database details fetches current tag options to guide filtering.
• Notion database search filters by keyword or tag to find the right record.
• Notion page content fetch pulls headers, paragraphs, and list items for rich answers.
• Set node formats sessionId and tag options so the agent stays scoped to the right data.

• Reduce time spent searching docs from 30 minutes to 2 minutes per question
• Automate answers to 60% to 80% of repeat questions
• Improve accuracy by pulling from a single Notion source of truth
• Handle 5 to 10 times more chat requests without adding headcount
• Connect Notion and OpenAI in one simple chat experience

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 Notion and OpenAI. See the Tools Required section above for links to create accounts with these services.
3. In Notion, create or choose a database for your knowledge base with question and answer fields. Add tags to help filter topics.
4. In Notion, create an internal integration and copy the Notion secret. Share your knowledge base database with this integration so it has access.
5. In the n8n credentials manager, create a new Notion credential using your Notion secret. Name it clearly, for example Notion KB.
6. Double click the Notion nodes: Get database details, Search notion database, and Search inside database record. In the Credential to connect with dropdown, select your Notion credential.
7. Open the Get database details node and choose your knowledge base database from the Database dropdown.
8. In the OpenAI Chat Model node, click Credential to connect with, create a new OpenAI credential, and paste your API key from the OpenAI API page.
9. Open the AI Agent node and confirm the language model, memory, and both Notion tools are connected to the agent inputs.
10. Click Chat in the top right of n8n to send a test question. You should see answers pulled from the Notion records that match your keywords or tags.
11. If you see The resource you are requesting could not be found, go back to Notion and make sure the database is shared with your integration.
12. Activate the workflow and copy the Chat URL from the When chat message received trigger for your team to use.