Be the first to know and get exclusive access to offers by signing up for our mailing list(s).

Subscribe

We ❤️ Open Source

A community education resource

3 min read

What happens when AI takes your meeting minutes

Discover how Read AI performs, what it does best, and its limitations.

This article is part of the eBook: Everyday AI guide: Practical genAI life hacks from real users, a free download from We Love Open Source.

Many of you already know that I dislike the stuff commonly referred to as AI. It’s not AI, it’s just interesting programming. But some of that programming can provide rather interesting results.

I frequently attend video conferences on Zoom, Jitsi, and Google Meet, but my most recent meeting introduced me to the Zoom tool, Read AI, to record and summarize meeting minutes.

Discovering Read AI

Just before the meeting was scheduled to begin, the organizer started the Read AI tool. I didn’t think any more about it even after I left the meeting. A couple hours later, I received an email that contained a quick summary of the meeting, and a link to Read AI.

I first needed to create an account — another one of many to keep track of and which might get hacked at some point. I tried the offer to use my Google credentials and was then asked to “allow” the meeting organizer to access my calendar and other info which I declined. I wasn’t given an option about my GMail account.

Exploring the meeting summary

After getting logged-in, I was presented with a chronological summary of the meeting as a series of notes, and a list of action items. It also included a video of the first 60 minutes of the meeting. Since the organizer used the free option, that’s all that was recorded.

The notes and action items were linked to the video at the point where they occurred. This is a really cool feature as it can prevent — or at least resolve — disagreements about who said what and when. Putting these events directly into the context of that part of the meeting can ensure that miscommunication is minimized.

I clicked on a tab for the complete transcript. That revealed the entire conversation up until the point at which the recording stopped.

But it does have problems. The main one I found is that, when people talk over each other, the program can’t distinguish who’s actually talking. Thus, in the transcript, the wrong person gets credited with something they didn’t say.

This Read AI is an interesting tool and produces results that are much better than any I produced when I was tasked with taking meeting minutes. Although someone trained and experienced at meeting minutes could have easily done that part.

What sets Read AI apart

The thing that sets this tool apart from humans is the full transcript, which couldn’t have been done on the fly, the links between the notes and action items to the video, and the speed with which those tasks were performed. It still has problems so it’s not where I would want to use it as an official tool for meetings that require complete accuracy. The transcript still needs to be checked by a human and compared to the video recording to ensure complete accuracy.

I see no real intelligence here. This is yet another example of some interesting and even clever programming. This is a tool that performs one task very well but not without problems.

Don’t ask it to do anything else such as analyze the content or verify facts. It can’t. Which makes it quite like virtually every other computer program ever written, whether touted as AI or not. It can only do exactly what it was trained to do.

Get the “Everyday AI” eBook

This free guide highlights simple, real-world examples of how people are using AI to save time, spark creativity, and make life easier.

Please enable JavaScript in your browser to complete this form.
We simply ask you to provide an email address to get the free download.
❤️ Love open source? So do 20,000+ devs. Get smarter, faster with the best tools, tips, and insights delivered weekly.

About the Author

David Both is an open source software and GNU/Linux advocate, trainer, writer, and speaker. He has been working with Linux and open source software since 1996 and with computers since 1969. He is a strong proponent of and evangelist for the "Linux Philosophy for System Administrators."

Read David's Full Bio

The opinions expressed on this website are those of each author, not of the author's employer or All Things Open/We Love Open Source.

Want to contribute your open source content?

Contribute to We ❤️ Open Source

Help educate our community by contributing a blog post, tutorial, or how-to.

We're hosting two world-class events in 2026!

Join us for All Things AI, March 23-24 and for All Things Open, October 18-20.

Open Source Meetups

We host some of the most active open source meetups in the U.S. Get more info and RSVP to an upcoming event.