> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.boundaryml.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.boundaryml.com/_mcp/server.

# Extracting Action Items from Meeting Transcripts

In this tutorial, you'll learn how to build a BAML function that automatically extracts structured action items from meeting transcripts. By the end, you'll have a working system that can identify tasks, assignees, priorities, subtasks, and dependencies.

## Prerequisites

* Basic understanding of BAML syntax
* An OpenAI API key configured in your environment

## Step 1: Define the Data Models

First, let's define the data structures for our tasks. Create a new BAML file called `action_items.baml` and add these class definitions:

```baml action_items.baml
class Subtask {
  id int
  name string
}

enum Priority {
  HIGH
  MEDIUM
  LOW
}

class Ticket {
  id int
  name string 
  description string
  priority Priority
  assignees string[]
  subtasks Subtask[]
  dependencies int[]
}
```

These models define:

* A `Subtask` class for breaking down larger tasks
* A `Priority` enum for task urgency levels
* A `Ticket` class that represents a complete task with all its metadata

## Step 2: Create the Task Extraction Function

Next, we'll create a function that uses GPT-4 to analyze meeting transcripts and extract tasks:

```baml action_items.baml
function ExtractTasks(transcript: string) -> Ticket[] {
  client "openai/gpt-4"
  prompt #"
    You are an expert at analyzing meeting transcripts and extracting structured action items and tasks.
    Extract all action items, tasks and subtasks from the meeting transcript below.
    For each task:
    - Generate a unique ID
    - Include who is assigned to it
    - Set appropriate priority level
    - Identify subtasks if any
    - Note any dependencies on other tasks

    {{ ctx.output_format }}

    {{ _.role("user") }} {{ transcript }}
  "#
}
```

This function:

* Takes a meeting transcript as input
* Returns an array of `Ticket` objects
* Uses GPT-4 to analyze the transcript
* Includes clear instructions in the prompt for task extraction

## Step 3: Test the Implementation

Let's add test cases to verify our implementation works correctly. Add these test cases to your BAML file:

```baml action_items.baml
test SimpleTranscript {
  functions [ExtractTasks]
  args {
    transcript #"
        Alice: We need to update the website by next week. This is high priority.
        Bob: I can handle that. I'll need Carol's help with the design though.
        Carol: Sure, I can help with the design part.
    "#
  }
}

test ComplexTranscript {
  functions [ExtractTasks]
  args {
    transcript #"
        Alice: Hey team, we have several critical tasks we need to tackle for the upcoming release. First, we need to work on improving the authentication system. It's a top priority.
        Bob: Got it, Alice. I can take the lead on the authentication improvements. Are there any specific areas you want me to focus on?
        Alice: Good question, Bob. We need both a front-end revamp and back-end optimization. So basically, two sub-tasks.
        Carol: I can help with the front-end part of the authentication system.
        Bob: Great, Carol. I'll handle the back-end optimization then.
        Alice: Perfect. Now, after the authentication system is improved, we have to integrate it with our new billing system. That's a medium priority task.
        Carol: Is the new billing system already in place?
        Alice: No, it's actually another task. So it's a dependency for the integration task. Bob, can you also handle the billing system?
        Bob: Sure, but I'll need to complete the back-end optimization of the authentication system first, so it's dependent on that.
        Alice: Understood. Lastly, we also need to update our user documentation to reflect all these changes. It's a low-priority task but still important.
        Carol: I can take that on once the front-end changes for the authentication system are done. So, it would be dependent on that.
        Alice: Sounds like a plan. Let's get these tasks modeled out and get started.
    "#
  }
}
```

These tests provide:

* A simple case with a single task and subtask
* A complex case with multiple tasks, priorities, dependencies, and assignees

This is what you see in the BAML playground:

<img src="https://files.buildwithfern.com/https://boundary.docs.buildwithfern.com/2026-06-19T22:23:03.688Z/assets/guide/action-items-simple.png" />

This is the output from the complex test case:

```output.txt
[
  {
    "id": 1,
    "name": "Improve Authentication System",
    "description": "Overhaul the authentication system focusing on both front-end and back-end aspects.",
    "priority": "HIGH",
    "assignees": ["Bob", "Carol"],
    "subtasks": [
      {
        "id": 2,
        "name": "Front-end Revamp"
      },
      {
        "id": 3,
        "name": "Back-end Optimization"
      }
    ],
    "dependencies": []
  },
  {
    "id": 4,
    "name": "Develop Billing System",
    "description": "Create a new billing system which will be integrated with the authentication system.",
    "priority": "MEDIUM",
    "assignees": ["Bob"],
    "subtasks": [],
    "dependencies": [3]
  },
  {
    "id": 5,
    "name": "Integrate Authentication System with Billing System",
    "description": "Integrate the improved authentication system with the new billing system.",
    "priority": "MEDIUM",
    "assignees": ["Bob"],
    "subtasks": [],
    "dependencies": [3, 4]
  },
  {
    "id": 6,
    "name": "Update User Documentation",
    "description": "Update the user documentation to reflect changes in the authentication and billing systems.",
    "priority": "LOW",
    "assignees": ["Carol"],
    "subtasks": [],
    "dependencies": [2, 5]
  }
]
```

## What's Next?

You can enhance this implementation by:

* Adding due dates to the `Ticket` class
* Including status tracking for tasks
* Adding validation for task dependencies
* Implementing custom formatting for the extracted tasks

## Common Issues and Solutions

* If tasks aren't being properly identified, try adjusting the prompt to be more specific
* If priorities aren't being set correctly, consider adding examples in the prompt
* For complex transcripts, you might need to adjust the model parameters for better results