This workflow creates an AI chatbot that uses your Notion database as a knowledge base and allows for website embedding (e.g., as a customer support chatbot). The AI agent can automatically query your Notion pages and databases to provide accurate, contextual responses based on your stored content.
This template is perfect for:
The workflow combines OpenAI's language model with Notion's database capabilities to create a smart chatbot. When users ask questions, the AI agent automatically determines which Notion pages or database entries are relevant and uses that content to generate helpful responses. The system maintains conversation history for natural, contextual interactions.
Add your credentials:
Configure your Notion connection:
Customize the AI model:
Test the chatbot:
Optional - Make it public:
Change the AI Provider:
You can replace the OpenAI Chat Model with other providers like Anthropic Claude, Google Gemini, or local models by swapping the language model node.
Adjust Context Window:
Modify the "Remember Chat History" node to increase or decrease how many previous messages the AI remembers (default is 10 interactions).
Update System Instructions:
Edit the Smart AI Agent's system message to change how the assistant behaves or add specific instructions for your use case.
Connect Multiple Databases:
Add additional Notion Database nodes to give the AI access to multiple databases or pages within your workspace.
Add More Tools:
Extend the AI agent with additional tools like web search, email sending, or integration with other services.
Chat Trigger → Smart AI Agent ← OpenAI Chat Model
↓
Set & Get Notion Database
↑
Remember Chat History
The Smart AI Agent orchestrates the conversation, deciding when to query Notion and how to use the retrieved content in responses. The memory buffer ensures natural conversation flow by maintaining context across interactions.