Free Intensive Nov 21–22Free 2-day hands-on Vibecoding Intensive on Nov 21–22 at 16:00 MSK (Sat–Sun) · Live Cohort 3 starts Nov 23Join Free →Cohort 3 (Nov 23)
ReleaseAPI / Product · ActionableThe Decoder→ original

Anthropic Teaches Claude to Join Google Meet Calls and Take Notes

Anthropic has launched Claude Meetings, which lets the AI join a video call as a visible participant that answers questions and keeps notes. During a meeting, Claude creates documents and whiteboards, records action items, and replies in text, and it reaches out to external tools only with permission. After the call, all notes, transcripts, and files sit on a dedicated page at claude.ai. For now, it's a beta for Team and Enterprise plans, and it only works with Google Meet.

AI-processed from The Decoder; edited by Hamidun News
Anthropic Teaches Claude to Join Google Meet Calls and Take Notes
Source: The Decoder. Collage: Hamidun News.
Listen to article
Article Fact Sheet & Key Figures
ParameterDetails
Primary sourceThe Decoder ↗
Editor-in-Chief
Key metric #1By default, Claude does not join calls with external participants
Key metric #2Not available to organizations under HIPAA or with client-side encryption
Key metric #3Anthropic promises to add platforms beyond Google Meet later

Every work meeting ends the same way: someone has to remember what was agreed, write up the summary, and assign the tasks. Usually the unluckiest participant does it, and not very well. Anthropic wants to hand this job to Claude. The company has launched Claude Meetings, a feature that adds AI to a video call as a full, visible participant that everyone can see.

What Claude does in a meeting

Claude appears in the participant list, and its presence is not hidden. During the call, you can ask it questions, and by default it answers in text rather than voice. This is convenient: the answer doesn't interrupt the conversation, and it lands in the chat where everyone can read it.

Besides answering, Claude can create documents and whiteboards right during the discussion. For example, a team debates a release plan while the assistant drafts a plan or a diagram. It also takes notes and records action items, meaning specific tasks with a clear owner and next step.

If the user grants permission, Claude can access connected tools. That means it isn't limited to what it heard on the call; it can pull data from services the company has opened to it. Without such access permission, it cannot do this.

After the meeting, everything is in one place. Notes, transcripts, and documents Claude prepared are gathered on a separate page at claude.ai. You don't need to dig through the chat for a file or ask a colleague to forward the minutes.

Limitations and privacy

The launch is cautious. The feature is in beta and available only on Team and Enterprise plans, so regular users can't access it. Of the video platforms, only Google Meet is supported. Anthropic says other services will follow, but the announcement gives no timeline.

There are also security restrictions. By default, Claude cannot join a call that includes external participants. For meetings with clients, contractors, and candidates, that is a significant limit, but it is also a reasonable safeguard: the AI won't record conversations with people who haven't agreed to work with a corporate assistant.

Organizations that operate under HIPAA (US requirements for protecting medical data) or use encryption where the customer controls the keys cannot use Meetings for now. For healthcare and heavily regulated companies, this rules out the feature entirely.

Why it matters

Claude Meetings continues a line Anthropic has been building recently. Boards and data dashboards recently appeared in the app, and together with Meetings they are gradually turning Claude from a chat tool into a general-purpose office tool. This is a response to competitors whose AI call assistants have already become a standard feature. Anthropic is now trying to keep users inside its ecosystem for the whole path from the meeting to the finished document.

For teams already paying for Team or Enterprise, the practical takeaway is simple: test the feature in internal meetings. Good candidates are standups, incident reviews, and retrospectives. There it's easy to compare Claude's notes with what people usually write and see how much actually falls out of the minutes.

Product teams should note the approach itself. The assistant doesn't hide in the background; it acts as a visible participant that replies in text and works only within the permissions it has been given. This setup addresses some trust concerns, though not all of them. The decision to record a meeting still has to be agreed with people, and the company must set its own policy for storing transcripts.

It's too early to judge quality: the announcement includes no accuracy figures and no data on how well Claude handles participants who talk over each other or have strong accents. This is a beta, and only real-world use will answer those questions. But the direction is clear: AI is increasingly present inside the workflow itself, not just next to it.

Story

Key Questions Answered

What Claude does in a meeting?

Claude appears in the participant list, and its presence is not hidden. During the call, you can ask it questions, and by default it answers in text rather than voice. This is convenient: the answer doesn't interrupt the conversation, and it lands in the chat where everyone can read it. Besides answering, Claude can create documents and whiteboards right during the discussion. For example, a team debates a release plan while the assistant drafts a plan or a diagram.

What are the key details on Limitations and privacy?

The launch is cautious. The feature is in beta and available only on Team and Enterprise plans, so regular users can't access it. Of the video platforms, only Google Meet is supported. Anthropic says other services will follow, but the announcement gives no timeline. There are also security restrictions. By default, Claude cannot join a call that includes external participants.

Why it matters?

Claude Meetings continues a line Anthropic has been building recently. Boards and data dashboards recently appeared in the app, and together with Meetings they are gradually turning Claude from a chat tool into a general-purpose office tool. This is a response to competitors whose AI call assistants have already become a standard feature. Anthropic is now trying to keep users inside its ecosystem for the whole path from the meeting to the finished document.

ZK
Zhemal Khamidun — CPO at Alpina Digital, product manager of AlpinaGPT. Building AI products since 2019. Hamidun News is a pet project that grew into a production aggregator with 6,000+ readers.
✦ Private AI Builders Community · Vibe Club

Ship AI Faster with Founders, Engineers & Weekly Architecture Reviews

Inside Vibe Club (hamidun.com/club) — weekly live masterminds with Zhemal Khamidun, Tech Radar, full LMS access, and 370+ production Claude Code skills.

Join Vibe Club →Explore Hamidun Academy
What do you think?
Loading comments…