AI Meeting Assistant

• Key points are in the visual diagram above.

Combines STT, diarization, NER, and integrations — a pattern every enterprise productivity team builds.

The colleague who sends the 'here's what we decided' email within 5 minutes of hang-up — with timestamps.

Scenario

45-min sprint planning. Output: 3 decisions (scope cut X), 5 Jira tasks with assignees, Slack message with link to timestamped transcript at decision moments.

Solution

In Capstone Projects, apply AI Meeting Assistant to this scenario: 45-min sprint planning. Identify the inputs, run the technique, validate the output, and note one thing you would monitor in production.

Do this before moving to the next module — reading alone is not enough.

Open the Code Walkthrough below and run it locally. Change one parameter related to AI Meeting Assistant (e.g. model, temperature, top_k, or tool name), observe the difference in output, and write 2–3 sentences explaining what changed.

Highlighted lines show where AI Meeting Assistant happens in the code.

1# AI Meeting Assistant — minimal example2from openai import OpenAI3
4client = OpenAI()  # create API client5
6# Ask the model to explain this topic7response = client.chat.completions.create(  # core API call for AI Meeting Assistant8    model="gpt-4o-mini",9    messages=[10        {"role": "system", "content": "You explain ai meeting assistant clearly."},11        {"role": "user", "content": f"What is ai meeting assistant?"},12    ],13    temperature=0,14)15print(response.choices[0].message.content)  # show output for debugging

• Summaries without speaker attribution
• Missing consent for recording
• Inventing action items not in transcript

Quick recap — the most important points from this module.