4 Chapter 3: AI Meeting Assistants

In the previous chapter, we explored how building a smart note-taking system like the Slip-box method can help transform scattered thoughts into a coherent and evolving knowledge network. But knowledge doesn’t only arise from solitary reading and reflection; it often emerges in real time, through conversations, meetings, lectures, and collaborative exchanges. This is where AI meeting assistants prove invaluable. They enable you to transcribe, summarize, and organize spoken content in real time producing a steady stream of raw material that can later be refined, connected, and incorporated into your Slip-box system.

If you’re anything like us, you’ve likely found yourself trying to stay engaged in a conversation while frantically scribbling notes, only to look back later and realize they’re incomplete, disorganized, or barely legible. It’s one of those all-too-familiar struggles in research: the constant tension between being fully present in a discussion and capturing what’s being said. More often than not, we end up sacrificing one for the other.

AI meeting assistants lift that burden by handling the listening and note-taking for you. Instead of dividing your attention between understanding and recording, you can focus entirely on the conversation, confident that everything is being transcribed, summarized, and organized in real time. It’s a shift from reactive note-taking to active participation.

And here’s the thing: trying to juggle both listening and note-taking doesn’t just stress you out, it actually undermines your ability to focus. As Ahrens (2017) points out, there’s a key distinction between different types of attention. “Focused attention” is what allows you to zero in on one thing but only for a few fleeting seconds at a time. Sustained attention, on the other hand, is what we need to stay locked into a task long enough to understand, learn, and retain new information. But when you’re constantly toggling between listening and writing, you interrupt that deeper kind of focus. That’s what makes AI meeting assistants so valuable: by offloading the task of transcription and note capture, they free up your cognitive resources so you can stay in that sustained mode of attention, fully present, fully engaged.

At this point, you might be asking: how are AI meeting assistants different from the AI note-taking tools discussed earlier? While both serve the broader goal of helping you capture, organize, and process information, they operate at different stages of the note-taking process. AI note-taking tools support the notes you actively create, enhancing them through features like summarization, tagging, and linking. AI meeting assistants, on the other hand, take a more hands-off role. They capture, transcribe, and summarize conversations as they happen. Instead of scrambling to take notes during a Zoom meeting or trying to recall what was said in a departmental discussion, these tools handle it for you, freeing up your attention to fully participate in the conversation.

What makes them particularly valuable in academic research is their ability to preserve context. AI meeting assistants don’t just record what was said, they identify who said it, distill action items, and often even organize the output into searchable, categorized notes. AI meeting assistants offer a way to stay present in the moment without sacrificing the detail and accuracy of your records. In this chapter, we’ll explore some of the leading tools in this area and look at how they can support, and even transform, your academic workflow.

Now what we want to do is make sure these AI meeting assistants aren’t just capturing information, they’re actually enhancing our Slip-box system. Once the meeting is transcribed and summarized, that’s when the real work begins. Go through the material, pull out the key insights, and turn them into permanent notes. Then, add them to your Slip-box, whether that’s in Obsidian, Notion, or another tool, linking them to relevant ideas you’ve already captured. This way, you’re actively building a network of thought that evolves over time.

1. Ethical Considerations for Using AI Meeting Assistants

Before we go any further, let’s pause to talk about something we’ll be repeating throughout this book: the ethical use of AI tools, especially AI meeting assistants.  As researchers, we’re not only working with data, we’re working with people. And that comes with serious ethical obligations. If you’re recording a conversation, whether it’s a research interview, a faculty meeting, or a casual brainstorming session, you must let people know. Ethically (and in many places, legally) you’re required to obtain their permission. Whether the tool is recording audio, transcribing speech, or generating a summary, the bottom line is the same: you’re collecting data from individuals, and they have a right to be informed.

Take, for example, a Zoom meeting where your AI assistant is quietly recording and transcribing in the background. It’s not enough to assume everyone notices the small “Recording” icon or the presence of a bot in the call. Make it explicit. A brief announcement at the start of the meeting –or better yet, a quick heads-up via email beforehand– goes a long way. And if you intend to use any of that material for research, be transparent about it. In fact, if you plan to quote someone directly in a paper or publication, we strongly recommend sharing the quote with them in advance and getting their approval. That small step builds trust and helps ensure you’re representing their words accurately and ethically.

Of course, not all situations are so straightforward. In public settings like academic conferences or panel discussions, getting individual consent may not always be practical. Still, we urge you to err on the side of caution. When in doubt, ask. Most people are just an email away and taking the time to request permission, especially when the material is personal or sensitive, demonstrates professionalism and respect.

In formal research contexts, particularly those involving interviews or participant-based studies, the ethical bar is even higher. Here are a few best practices to keep in mind:

• Be transparent: Before recording, clearly explain your intention and purpose. Let participants know if you’re using an AI tool and what it will be capturing.
• Get explicit consent: Don’t assume implied agreement. Secure verbal or written confirmation, depending on the context.
• Clarify usage: Be clear about how the data will be used. Is it strictly for your own notes? Will quotes appear in a publication? Will the audio be stored or shared?
• Anonymize when needed: If you’re dealing with sensitive information, take care to remove or obscure identifying details especially in transcripts or published work.
• Invite participant review: When possible, share transcripts or key quotes and ask if participants are comfortable with how their ideas are being represented.

2. AI Meeting Assistants

Let’s explore together some of our favourite AI meeting assistants and how they can facilitate your note-taking.

2.1.  tl;dv

tl;dv is a powerful AI assistant that automatically records the meetings you conduct on Zoom, Google Meet, or Microsoft Teams. What’s even better is that tl;dv right after your meeting ends, it gives you an AI-generated summary that captures key points, action items, and decisions. You don’t need to replay the whole call or scroll through pages of transcript, tl;dv distills the conversation into something you can quickly scan and act on. And you can even tailor the summaries to suit your research workflow.

tl;dv comes with a powerful search functionality. You can search for a specific concept, quote, or keyword and instantly jump to that part of the transcript. You can also pull out clips from your recordings. Say a colleague makes a sharp point during a discussion, or a research participant offers a quote you want to use, you can highlight that moment, clip it, and share it. No need to send the whole meeting file. It’s precise and shareable. You can even get scheduled summaries sent to your inbox like a running digest of your research discussions over time. Super helpful when you’re trying to spot patterns or piece together findings from multiple conversations. Additionally, tl;dv recognizes who’s speaking and organizes your transcripts accordingly. With timestamped notes, you can navigate your recordings with ease, reviewing exactly what was said and when.

2.2. Fathom

Fathom is another robust AI meeting assistant that lets you keep up with note-taking while engaging in your meetings. Fathom automatically records, transcribes, and summarizes your discussions on Zoom, Google Meet, and Microsoft Teams so you can focus on the conversation. As your meeting unfolds, Fathom detects key decisions, follow-ups, and next steps, turning them into a tidy list of actionable takeaways. You can also highlight important moments in real time, so if a participant shares a compelling insight or someone drops a useful citation or research idea, just tap to mark it.

Searching for specific details in a meeting is also super easy. Simply type in your search term and Fathom will jump straight to the part of the recording where the term is mentioned. Better yet, with the Ask Fathom feature, you can query your meetings like a chatbot. You can ask any question and Fathom replies with insights from the meeting.  Collaboration is seamless, too. You can share summaries, key moments, and action items with your research team instantly.

2. 3. Fireflies

Fireflies makes it incredibly easy to record, transcribe, and analyze your meetings. Whether you’re attending research meetings, conducting interviews, or participating in academic discussions, Fireflies allows you to capture, transcribe, and summarize every important detail.

To get started, simply invite Fireflies’ AI notetaker bot to your scheduled meetings on Zoom, Google Meet, or Microsoft Teams. The bot will automatically join, record, and transcribe the conversation in real-time. If you need to transcribe in-person discussions, Fireflies also offers a mobile app that allows you to record and summarize any conversation.

One of the most valuable features for researchers is AI-powered summaries and action items. Instead of reviewing long transcripts, you get concise notes that highlight key discussion points, important decisions, and next steps. You can even customize your summaries based on your needs, whether you want a simple overview, bullet points, or a structured breakdown of discussion topics.

For those who want to go beyond basic note-taking, Fireflies offers AskFred, an AI assistant that lets you query your meeting recordings for specific insights. If you need a summary of an entire semester’s research discussions or key findings from multiple meetings, just ask Fred, and it will generate a clear and concise response.

2. 4. Otter

Otter AI is one of those tools I keep coming back to so much so that you’ll find it featured across different sections of this book. When it comes to meetings, Otter will help take the pressure off giving you live transcriptions, automatic summaries, and a fully searchable record of your conversations.  As the meeting rolls on, Otter transcribes in real time. It even identifies different speakers which is incredibly useful when you’re trying to make sense of multi-voice discussions later. And thanks to its powerful search function, finding a specific quote or idea from a past meeting takes seconds.

And like previous AI meeting assistants, Otter also supports collaborative features. You can highlight parts of the transcript, leave comments, tag colleagues, and even drop in images. It’s perfect for research teams who want to keep their ideas organized and accessible without bouncing between a dozen platforms.

The real magic, though, is in OtterPilot. Once connected to your calendar, it can automatically join scheduled Zoom, Google Meet, or Microsoft Teams meetings, transcribe the conversation, and generate a summary. You can also use Otter beyond meetings. Upload pre-recorded lectures, interviews, or videos, and get full transcripts in minutes (I discussed this feature in detail in AI for Data Collection chapter).

2. 5.  Zoom AI Companion

Zoom AI Companion is definitely a must-have if you use Zoom for your meetings. It does pretty much the same task as previous tools: it handles recording, transcribing, summarizing, and even analyzing your meetings all without interrupting your flow.

The tool also includes an interesting AI feature which is Meeting Summaries with AI Companion. Once enabled, it creates a summary of your meeting automatically, no need to hit the record button or do anything extra. Just talk and Zoom handles the rest. You can even decide who gets access to the summary: just you, your whole team, or even external collaborators. To turn it on, head to your Zoom web portal, go to Settings > AI Companion, and toggle on “Meeting Summary.”

Another key feature provided by Zoom is Zoom’s Smart Recording which besides recording meetings, provides you with a host of analytic features to help you make sense of your recordings. These include highlighting key moments, breaking sessions into chapters, and extracting action items for you.

And here’s where it gets really clever: if you join a meeting late or get momentarily distracted, you can just ask AI Companion to catch you up. Want to know if someone mentioned your name? What action items have come up? What’s the status of a certain topic? Just ask.

Zoom AI Companion also goes beyond note-taking with features like meeting coaching. It can analyze your talk-to-listen ratio, pacing, filler word usage, and engagement. If you’re presenting research or leading a group discussion, these insights can help you sharpen your delivery and communication style over time.

2. 6. Notta

Notta AI is a powerful AI-powered transcription tool that can help you with your meetings. Notta automatically records, transcribes, and summarizes meetings and interviews across platforms like Zoom, Google Meet, and Microsoft Teams. Notta supports real-time transcription converting speech to text instantly.

Another key feature is the ability to highlight key moments. This is incredibly helpful when a participant mentions an important reference or insight, you can flag it immediately, without breaking your attention. If you work with collaborators from different parts of the world, you’ll also appreciate Notta’s multi-language support. It handles transcription in over 50 languages and even recognizes bilingual conversations, so when two or more languages are spoken during the same meeting, it still captures everything accurately.

Notta also provides a plethora of features that help you interact and make sense of your transcripts. For instance, its AI-powered summaries can help you distill the key takeaways, action items, and decisions from your transcript. You also get speaker identification, which is essential for parsing group conversations and making sure you know who said what. Additionally, Notta’s “AI Notes” feature lets you generate summaries using templates or build your own if you prefer a custom format that fits your research workflow.

2. 7. Rev AI

If you’re doing research that involves interviews, lectures, or live discussions, Rev AI is a tool worth having in your toolkit. It’s a speech recognition platform built to handle transcription, captioning, and content analysis all powered by AI. And like other tools, Rev doesn’t just transcribe, it also helps you make sense of your audio data quickly and in a format you can immediately work with.

Let’s say you’ve recorded a seminar or an in-depth interview. With Rev’s asynchronous transcription, you just upload your file, audio or video, and get a transcript back in minutes. For live sessions like conferences or research panels, Rev’s real-time streaming transcription captures every word as it happens. And if you’re working with sensitive material or need extra precision, there’s always the option to order human transcription.

Rev offers an interactive editor which makes it easy to clean up your transcript, edit speaker names, fix typos, and reformat sections without opening another tool. And when it comes to multilingualism, Rev supports transcription in over 58 languages for uploads and 9 languages for live streaming.

Conclusion

As we’ve seen throughout this chapter, AI meeting assistants are quickly becoming indispensable partners in the academic workflow. In this chapter, we’ve focused primarily on their note-taking functionalities, showing how these tools do far more than simply capture what was said. From live transcription to smart summaries, speaker identification, and even advanced analytics like sentiment detection, these tools bring a level of structure and intelligence to your research meetings that would be nearly impossible to achieve manually.

What makes these tools especially powerful is that they don’t just record, they help you understand. The AI-powered features built into these platforms enable you to generate summaries, extract insights, identify key decisions, tag speakers, and in some cases, analyze tone and emotional cues. That’s not just note-taking, that’s assisted comprehension. And in research, where ideas evolve through dialogue, this kind of automated reflection is very important.

As we mentioned earlier, several of the tools covered here also appear in other chapters, particularly those on data collection and data analysis. And that’s no accident. The versatility of these tools means you can use the same platform across multiple phases of your research, from recording interviews and transcribing lectures, to generating qualitative data, analyzing themes, creating translations, and more. That kind of continuity is invaluable when you’re managing a complex project.

Now, if you’ve already built a slip-box using a comprehensive note-taking platform like Obsidian or Notion, here’s where the real synergy begins. AI meeting assistants can serve as input channels capturing rich, spontaneous conversations and turning them into structured content. But don’t stop at the transcript. Instead, use these outputs as a springboard for deeper thinking. Create your own notes from them, paraphrase important points, highlight tensions or contradictions, pose follow-up questions, and connect those insights to ideas already stored in your slip-box.

This step is essential. It’s what transforms passive content into active knowledge. When you summarize in your own words, link new notes to existing ones, and revisit key themes, you’re not just filing information, you’re actually making meaning. As we discussed in the previous chapter, the real value of a slip-box lies in its network of connections. New notes only become powerful when they’re connected to what you already know. That’s when your knowledge becomes dynamic and capable of generating insights, surfacing gaps, and guiding your next steps. In the next chapter, we talk about mind mapping tools and explain how they can help you capture notes in a non-linear way.