BroxiAI
  • Welcome
  • Account
    • Quickstart
    • Password
    • Team
      • Create team
      • Join team
      • Payment & Billing
      • Payment Policy
    • Global Variables
    • API Keys
  • Workflow
    • Overview
    • Quickstart
    • Components
    • Playground
    • Publish Workflow
    • File Manager
    • Webhook
  • Components
    • Input & Output
    • Agents
    • AI Models
    • Data
    • Embeddings
    • Helper
    • Loader
    • Logic
    • Memories
    • Processing
    • Prompt
    • Tools
    • Vector database
  • Advanced
    • Use Agent in flow
    • MCP Connect
    • MCP Astra DB
  • Integration
    • Apify
    • AssemblyAI
    • Composio
    • Google
      • Google Auth
      • Vertex AI
    • Notion
      • Setup
      • Notion Conversational Agent
      • Notion Meeting Notes Agent
Powered by GitBook
On this page
  • Prerequisites​
  • Components​
  • Flow Process​
  • Run the Notion Meeting Notes flow​
  • Customization​
  • Troubleshooting​
  1. Integration
  2. Notion

Notion Meeting Notes Agent

PreviousNotion Conversational Agent

Last updated 12 days ago

The Notion Agent for Meeting Notes is an AI-powered tool that automatically processes meeting transcripts and updates your Notion workspace. It identifies tasks, action items, and key points from your meetings, then creates new tasks or updates existing ones in Notion without manual input.

Prerequisites


Before using this flow, ensure you have obtained the necessary API keys from Notion and OpenAI. These keys are essential for the flow to function properly. Keep them secure and do not share them publicly.

Components


Notion Meeting Agent Part 1

This component allows users to input the meeting transcript directly into the flow.

  • Purpose: Retrieves a list of users from the Notion workspace.

  • Input: Notion Secret (API key)

  • Output: List of user data

  • Purpose: Searches and lists all databases in the Notion workspace.

  • Input:

    • Notion Secret (API key)

    • Query (optional)

    • Filter Type (default: database)

    • Sort Direction

  • Output: List of database data

This component creates a dynamic prompt template using the following inputs:

  • Meeting Transcript

  • List of Users

  • List of Databases

  • Current Date

  • Purpose: Analyzes the meeting transcript and identifies tasks and action items.

  • Inputs:

    • System Prompt (from the Prompt component)

    • Language Model (OpenAI)

    • Tools:

      • Notion Search

      • List Database Properties

      • Create Page

      • Update Page Property

      • Add Content to Page

  • Purpose: Executes actions in Notion based on the meeting summary.

  • Inputs:

    • System Prompt (from the second Prompt component)

    • Language Model (OpenAI)

    • Tools:

      • List Database Properties

      • Create Page

      • Update Page Property

      • Add Content to Page

  • Purpose: Retrieves the properties of a specified Notion database.

  • Input:

    • Database ID

    • Notion Secret (API key)

  • Purpose: Creates a new page in a Notion database.

  • Inputs:

    • Database ID

    • Notion Secret (API key)

    • Properties (JSON)

  • Purpose: Updates the properties of an existing Notion page.

  • Inputs:

    • Page ID

    • Notion Secret (API key)

    • Properties to update

  • Purpose: Converts markdown text to Notion blocks and appends them to a specified Notion page.

  • Inputs:

    • Page/Block ID

    • Notion Secret (API key)

    • Markdown text

Displays the final output of the Notion Agent in the Playground.


  1. The user inputs a meeting transcript.

  2. The flow retrieves the list of Notion users and databases.

  3. A prompt is generated using the transcript, user list, database list, and current date.

  4. The Meeting Summarizer analyzes the transcript and identifies tasks and action items.

  5. The Notion Agent uses the meeting summary to:

    • Create new pages for new tasks

    • Update existing pages for existing tasks

    • Add content to pages with meeting notes

  6. The Chat Output displays a summary of actions taken in Notion.


To run the Notion Agent for Meeting Notes:

  1. Open BroxiAI and create a new workflow.

  2. Add the components listed above to your flow canvas.

  3. Connect the components as shown in the flow diagram.

  4. Input the Notion and OpenAI API keys in their respective components.

  5. Paste your meeting transcript into the Meeting Transcript component.

  6. Review the output in the Chat Output component, which will summarize the actions taken in your Notion workspace.

For optimal results, use detailed meeting transcripts. The quality of the output depends on the comprehensiveness of the input provided.


The flow can be customized to meet your team's specific needs.

Customize this flow by:

  1. Adjusting the system prompt to change the agent's behavior or knowledge base.

  2. Adding or removing Notion tools based on your specific needs.

  3. Modifying the OpenAI model parameters (e.g., temperature) to adjust the agent's response style.


If you encounter issues:

  1. Ensure all API keys are correctly set and have the necessary permissions.

  2. Check that your Notion integration has access to the relevant pages and databases.

  3. Verify that all components are properly connected in the flow.

  4. Review the BroxiAI logs for any error messages.

Meeting Transcript (Text Input)

List Users (Notion Component)

List Databases (Notion Component)

Prompt

Meeting Summarizer (Tool Calling Agent)

Notion Meeting Agent Part 2

Notion Agent (Tool Calling Agent)

Notion Components (Tools)

List Database Properties

Create Page

Update Page Property

Add Content to Page

Chat Output

Flow Process

Run the Notion Meeting Notes flow

Run the flow by clicking on the Chat Output component.

Customization

Troubleshooting

For more advanced usage and integration options, refer to the and .

​
​
​
​
​
​
​
​
​
​
​
​
​
​
Playground
​
​
Notion API documentation
Langflow documentation
​
Notion App
Notion API key
OpenAI API key
​