7.2 Meeting Recap, Transcripts & Catch-Up

Microsoft AI Business Professional AB-730

Track your progress as you read

Finished sections get a check mark.

1 Introduction & Exam Overview

0.1 About the AB-730 Exam 0.2 How to Use This Study Guide

2 Chapter 1: Understand Generative AI Capabilities Across Microsoft 365

1.1 How Copilot Works: LLMs, Microsoft Graph & the Security Boundary 1.2 Context & Grounding: Work Files, Web Data and App Context 1.3 Chat Experiences vs. Agent Experiences 1.4 When to Create Your Own Agent 1.5 Copilot Capabilities Across Microsoft 365 Apps

3 Chapter 2: Responsible AI & Data Protection Practices

2.1 Generative AI Risks: Fabrications, Prompt Injection & Over-Reliance 2.2 Verification Steps: Citation Checks & Human Review 2.3 Recognizing & Mitigating Risks to Sensitive Data 2.4 How Data Protection Restricts Prompt Results

4 Chapter 3: Creating and Managing Prompts

3.1 Creating an Effective Prompt: The GCSE Framework 3.2 Selecting Resources to Reference in a Prompt 3.3 Saving and Sharing Prompts in Copilot Prompt Gallery 3.4 Scheduling Prompts

5 Chapter 4: Managing Conversations and Notebooks

4.1 Finding Previous Conversations 4.2 Renaming and Deleting Chats 4.3 Adding a Conversation to a Copilot Notebook

6 Chapter 5: Creating and Managing Microsoft 365 Copilot Agents

5.1 Agent Store vs. Creating a New Agent 5.2 Creating an Agent from a Template 5.3 Configuring an Agent That Has Knowledge 5.4 Configuring Instructions, Capabilities & Suggested Prompts 5.5 Sharing an Agent with Team Members

7 Chapter 6: Drafting and Analyzing Business Content

6.1 Creating a New Document from a Prompt 6.2 Generating a Document from an Existing Document 6.3 Generating a Management Summary 6.4 Moving Data & Insights Between Microsoft 365 Apps 6.5 Drafting Communications with Copilot in Outlook

8 Chapter 7: Meetings, Collaboration and Personalization

7.1 Using Copilot for Meetings: Setup & Live Intelligence 7.2 Meeting Recap, Transcripts & Catch-Up 7.3 Copilot Pages for Collaboration 7.4 How Copilot Uses Memory & Instructions

7.2 Meeting Recap, Transcripts & Catch-Up

Key Takeaways Explain This Topic AI

Intelligent recap requires the meeting to have been transcribed or recorded; without a transcript there is nothing for Copilot to summarise afterwards.

Recap delivers AI notes, key points, and action items, plus speaker and topic markers that let you jump to the moment a decision was made.

Copilot answers post-meeting questions from the transcript, so it can only report what was actually said aloud.

The catch-up workflow is ask, verify against the timeline marker, then act — never forward a recap you have not spot-checked.

Assigned action items are suggestions drawn from the conversation; ownership is not authoritative until a human confirms it.

Last updated: August 2026

7.2 Meeting Recap, Transcripts & Catch-Up

Quick Answer: Post-meeting Copilot is transcript-powered . If the meeting was transcribed or recorded, you get intelligent recap — AI notes, key points, action items, speaker attribution and topic markers — and you can ask Copilot questions about what happened. If it was not transcribed, none of that exists afterwards, no matter how the meeting itself went.

This is the single most testable fact in the meetings portion of the blueprint, and it is also the one that generates the most real-world disappointment. A user who joins a meeting, relies on Copilot, and never enables transcription has no post-meeting artifact at all.

1. Post-Meeting Intelligence: Intelligent Recap, Decision Logs & Action Tables

Once a transcribed meeting ends, Microsoft 365 Copilot processes the entire conversation to generate an Intelligent Recap located directly in the meeting's Recap tab within Microsoft Teams. ┌─────────────────────────────────────────────────────────────────────────────┐

│ TEAMS INTELLIGENT RECAP ARCHITECTURE │
├─────────────────────────────────────────────────────────────────────────────┤
│ [AI-GENERATED NOTES & SUMMARY] │
│ • Executive overview of discussion topics and strategic outcomes │
│ • Editable by meeting organizers and participants │
│ │
│ [TOPIC CHAPTERS & TIMELINE MARKERS] │
│ • Meeting split into thematic sections (e.g., "00:00 - Architecture", │
│ "14:20 - Budget Variance", "32:10 - Implementation Roadmap") │
│ • Direct jump links to video recording playback points │
│ │
│ [PERSONALIZED SPEAKER & NAME MENTION MARKERS] │
│ • Visual timeline flags indicating exactly when you were mentioned │
│ • Markers showing when your name was cited in connection with a task │
│ │
│ [STRUCTURED DECISION LOGS & ACTION MATRICES] │
│ • Table: [Action Item | Assigned Owner | Target Deadline | Context Link] │
│ • Automated sync with Microsoft To Do and Microsoft Planner │
└─────────────────────────────────────────────────────────────────────────────┘
1. AI-Generated Notes & Key Points

Copilot automatically synthesizes the full transcript into structured thematic bullets. Rather than recording chronological back-and-forth remarks, it identifies core themes, strategic pivots, and final conclusions.

2. Topic Chapters & Content-Based Navigation

For long meetings (e.g., 60–120 minutes), navigating a raw recording is inefficient. Intelligent Recap creates Topic Chapters by analyzing semantic shifts in dialogue. Users can click on a chapter title (e.g., "Discussion on Security Compliance" ) to jump the video recording directly to the exact second that topic began.

3. Personalized Timeline Markers

Copilot tailors the recap interface to the individual user:

Name Mention Markers: Flags on the playback timeline indicating where other participants mentioned the user's name.

Speaking Markers: Highlighting where the user spoke on the call.

Screen Share Markers: Indicating when slides or screens were presented.

4. Decision Logs vs. Action Item Tables

A hallmark of effective governance is distinguishing between what was decided and what must be done :

Output Component Definition & Purpose Example Structure

Decision Log Formal record of strategic consensus, approved budgets, or rejected alternatives "Decision: The steering committee approved Option B (AWS to Azure migration) with a budget cap of $450,000."

Action Item Matrix Operational assignments extracted from explicit and implicit verbal commitments Markdown/Planner table with columns: [Action Item] , [Assigned Owner] , [Target Deadline] , [Source Context] +---------------------------------------------------------------------------------------+

| SYNTHESIZED ACTION ITEM MATRIX EXAMPLE |
+---------------------------------------------------------------------------------------+
| ACTION ITEM | ASSIGNED OWNER | TARGET DUE DATE | CONTEXT / SOURCE |
+--------------------------------+----------------+-----------------+-------------------+
| Finalize Purview DLP policies | Sarah Chen | Oct 14, 2026 | Discussed @ 18:22 |
| Revise cloud migration SOW | David Ortiz | Oct 18, 2026 | Discussed @ 34:10 |
| Schedule vendor security audit | Elena Rostova | Oct 22, 2026 | Discussed @ 51:05 |
+---------------------------------------------------------------------------------------+
The Catch-Up Workflow

Missing a meeting is the scenario the blueprint has in mind when it says "describe how to use Microsoft 365 Copilot for meetings". The efficient sequence is:

Orient. "Summarise this meeting in five bullets." You now know whether the meeting mattered to you.

Narrow. "What was decided about the launch date, and who raised concerns?" Copilot answers from the transcript and points at the moment.

Verify. Jump to the cited timeline marker and read the actual exchange. This takes seconds and is the step that separates a reliable catch-up from a confidently wrong one.

Extract your own tasks. "What was assigned to me?" Then confirm ownership with the person who assigned it.

What Copilot Cannot Recover

Not captured Consequence
Anything said before transcription started Early decisions are missing from recap
Content shown on screen but never described aloud A slide's numbers do not enter the transcript
Side conversations in private chat Objections raised privately never surface
Tone, hesitation, and reluctant agreement "Agreed" reads as consensus even when it was not

On the Exam: Action items produced by recap are suggestions derived from what was said , not authoritative assignments. Any item that reads as a firm commitment should be confirmed with the named owner before it is treated as a task.

Recording, Transcription, and Which One Copilot Needs

Candidates routinely treat "recorded" and "transcribed" as one setting. They are not, and the distinction decides whether post-meeting Copilot works at all.

Recording Transcription
What it produces Audio and video of the meeting The text of what was said, attributed to speakers
What Copilot uses afterwards Nothing directly This — the transcript is the grounding data
If only this one is on Post-meeting Copilot has no text to reason over Recap works even with no video saved

The practical instruction for anyone who wants a usable recap is therefore not "hit record" but make sure the meeting is transcribed . An organiser who records without transcription ends up with an hour of video and a Copilot that cannot answer a single question about it.

On the Exam: When a scenario says a meeting was held but Copilot cannot summarise it afterwards, the missing prerequisite is the transcript , not a licence, not an admin setting, and not indexing delay.