Claude Meetings Puts Claude in Your Google Meet Calls, Building Docs and Whiteboards While You Talk

Anthropic's Claude Meetings beta adds Claude to Google Meet calls as a visible participant that answers questions, writes notes and builds docs and whiteboards while the team talks. It is limited to Team and Enterprise plans, skips calls with outside guests by default and saves transcripts, not audio.

Christopher Ort
By Christopher Ort · 8 min read
Share
Two colleagues at a conference table with laptops and coffee cups follow a video call on a large wall display.
Image: AI-generated, i10X
On this page
  1. Quick Take
  2. In plain English
  3. What happened
  4. How it works
  5. Background: from notetaker bots to co-workers in the call
  6. Pros and cons
  7. What X is saying
  8. Grok's take
  9. Critical analysis
  10. What's still open
  11. About the analysis
  12. i10x Perspective

Somebody always has to take the notes. Anthropic wants that somebody to be Claude, and it wants Claude to do a lot more than write them. The company has introduced Claude Meetings, announced on X on November 12, 2026, a beta that adds Claude to a Google Meet call as a visible participant. It follows the conversation, answers questions in the chat and builds docs and whiteboards while people are still talking. The launch post on X passed 80,000 likes, and within hours the replies had declared half the meeting-notes industry dead. The reality is more interesting, and more limited.

i10X Quick Take

Quick Take

  1. What launched: Claude Meetings, a beta that lets Claude join Google Meet calls, answer questions out loud or in chat, write notes and action items and build docs, whiteboards and other artifacts live.
  2. Who gets it: Claude Team and Enterprise plans. On Team it is on by default; on Enterprise an admin has to switch it on. Organizations with zero data retention, HIPAA-ready setups or customer-managed encryption keys are excluded during the beta.
  3. What it costs: Notes, transcripts and in-call answers are free during the beta. Docs, whiteboards and other artifacts made in a call are free through February 10, 2027. Answers that use connected tools count toward plan usage.
  4. Privacy defaults: Claude stays out of calls with outside guests and leaves if one joins, unless an admin allows it. It saves a transcript, summary and screen descriptions, not audio.
  5. Why it matters: Meeting AI is moving from “summary afterwards” to “work during the call”, and Anthropic is entering a crowded field where SpaceXAI’s Grok Bot announced its own meeting support on November 13.

In plain English

Claude, Anthropic’s AI assistant, can now sit in on a company’s video calls like an extra colleague. Everyone can see it in the list of people on the call. You can ask it a question, have it write up the plan you are discussing, or sketch a timeline on a shared board, and your team can fix its work while the meeting continues. Afterwards, the notes and the to-do list are already written. For now it only works in Google Meet and only for businesses that pay for Claude’s team plans.

What happened

Anthropic announced Claude Meetings on its own blog and on X. “Introducing Claude Meetings: add Claude to your team’s video call and it builds docs, whiteboards, and other artifacts with you while you’re still talking,” the @claudeai account wrote. The follow-up posts added that Claude “joins as a visible participant” and that the product is “starting with Google Meet, with support for other video conferencing platforms coming soon.”

Anthropic’s announcement walks through an example: a team planning a customer event says “Claude, start a doc for this plan.” Claude writes up what has been said so far, and teammates on the invite edit it as the talk continues. When someone asks what last year’s event cost, Claude asks for permission to look it up in connected tools, posts the answer in the meeting chat and compares it to the current plan. After the call, notes, action items, the plan and the whiteboard sit on a meeting page in claude.ai.

Anthropic also says it is “working with partners like Gong, Attention, Granola, Fireflies.ai, Otter, and Plaud” so teams can send a meeting’s transcript to tools they already use. That detail matters for the “Anthropic just killed every notetaker” takes on X: several of the named “victims” are launch partners.

How it works

According to Anthropic’s announcement and the setup guide by The AI Leverage, the flow looks like this:

  • Connect a calendar. An owner enables Google Calendar for the organization. Users then connect their calendar under Meetings in Claude.
  • Add Claude to a meeting. Pick a meeting and click Add Claude, or turn on auto-join. If Claude has to ask to enter, the host can admit it; if the host declines, Claude does not retry unless someone adds it again.
  • Talk to it. Ask out loud or in the chat. By default Claude answers in writing in the Meet chat. For spoken requests, Claude currently asks each time to confirm who is speaking.
  • Build together. Claude creates docs, whiteboards and other artifacts that people on the invite can edit during the call.
  • Afterwards. A separate meeting page holds notes, transcript and anything Claude built. Users can later ask Claude questions about meetings they attended.

The guide adds that Claude can stay in a call for up to eight hours and warns before it leaves. Admins get three switches: whether Claude Meetings is on, whether it may join meetings with external guests, and whether members’ connected tools can be used in calls.

Background: from notetaker bots to co-workers in the call

AI meeting assistants are not new. A long list of startups, from Otter and Fireflies to Granola and Fathom, record or transcribe calls and send summaries afterwards. Google has its own Gemini features inside Meet. What Anthropic is pitching is different in emphasis: Claude is supposed to start the actual work product during the meeting, using the same docs and whiteboard features Anthropic has been shipping in recent weeks.

The timing is also competitive. On November 13, SpaceXAI’s Grok Bot announced that it “can now join meetings.” According to the Grok Bot documentation, a bot can join Google Meet, Zoom or Microsoft Teams calls on Team, Enterprise and Ultra plans, takes notes, answers in the meeting chat and sends a summary and action items afterwards. i10x has covered how Grok Bot users run whole teams of agents. Anthropic, for its part, opened self-hosted Claude Managed Agents the same day as Meetings, and is heading toward its Nasdaq listing with a steady stream of workplace features.

Pros and cons

For users

  • Pro: Nobody has to take notes, and decisions turn into a draft doc or whiteboard before the call ends, while everyone can still correct it.
  • Con: Google Meet only, and only on paid business plans. Claude answers in text, not voice, and spoken requests trigger a speaker check each time.

For developers

  • Pro: Connected tools work inside calls with each person’s permission, so internal data can feed live answers without copy and paste.
  • Con: There is no public API for Claude Meetings mentioned in the launch materials, so teams cannot yet build custom in-call workflows on top of it.

For companies

  • Pro: Sensible defaults: no external guests, a visible participant, a chat notice, no audio storage, and admin controls per role. Notes and transcripts cost nothing extra during the beta.
  • Con: Excluded for zero-data-retention, HIPAA-ready and CMEK customers, which are often exactly the regulated firms with the most meetings. Pricing for artifacts after February 10, 2027 is unknown, and transcription still requires everyone’s consent.

What X is saying

Anthropic’s launch post set the tone:

Product manager Matt Piccolella described the build in personal terms:

The most shared reaction was a list. @robj3d3 posted “Anthropic just killed:” followed by more than 25 meeting tools, from Otter and Granola to Gong. Others were more measured. “I’d let it start the notes. I’d still review every doc first,” wrote @AdamJWenborn, adding: “Hoping Microsoft Teams follows soon for my 9-5.” Consultant @PatSchaber called it “simply phenomenal” and wondered what other meeting transcript companies “are going to do to differentiate themselves from this.”

Grok Bot’s own meeting launch landed the next day:

Grok’s take

Asked to compare the two, Grok replied: “Grok Bot joins Meet, Zoom, and Teams, takes notes, answers in chat, and delivers a summary plus action items after. Claude Meetings focuses on live docs, whiteboards, and real-time artifacts inside Google Meet.” In other replies, Grok repeatedly pointed out that Claude Meetings is Google Meet only for now and limited to Team and Enterprise plans, with no timeline for individual plans.

Critical analysis

The “Anthropic killed 27 startups” meme makes for a fun scroll, but it skips two facts. First, several of those companies (Gong, Attention, Granola, Fireflies.ai, Otter) are named by Anthropic as partners that will receive Claude’s transcripts. Second, Claude Meetings covers one video platform and two paid plans. Dedicated tools that work across Zoom, Teams and phone calls are not obsolete this week.

The more serious shift is the job description. A notetaker records what was said. Claude Meetings tries to produce what was decided, in the form of a document or a whiteboard, while the people who decided it are still in the room. That shortens the loop between talking and doing, and it raises a new quality question: a draft written live from a messy conversation can lock in a misunderstanding just as quickly as it captures a decision. Anthropic’s design, with visible artifacts that teammates can correct during the call, is a sensible answer, but it only works if someone actually reads them.

On privacy, the defaults are cautious: no outside guests, an automatic exit when one joins, no audio storage, a chat notice. The open issue is consent. Anthropic explicitly asks customers to make sure everyone is fine with being transcribed, which puts the legal burden on the customer, not the tool.

What’s still open

  • When Zoom, Microsoft Teams and other platforms will be supported. Anthropic only says “coming soon.”
  • What docs, whiteboards and other in-call artifacts will cost after February 10, 2027.
  • When, or whether, Pro and Max subscribers get access.
  • When regulated customers with zero data retention, HIPAA-ready configurations or CMEK will be able to use it.
  • When the transcript export to partners like Gong, Granola and Otter actually goes live.

About the analysis

Researched and written with AI assistance under the editorial responsibility of the i10X News team. The title image is an AI-generated image. Read our AI Use Policy. Spotted an error? Request a correction.

This independent i10x analysis is based on Anthropic’s announcement, launch posts on X, reporting by VentureBeat and Gadgets 360, a third-party setup guide and SpaceXAI’s Grok Bot documentation for comparison. i10x did not test Claude Meetings.

i10x Perspective

Claude Meetings is a bet that the most valuable minute of a meeting is the one right after a decision, when someone has to turn talk into a plan. If Claude can draft that plan while the team watches, meetings stop producing homework and start producing documents. The beta is narrow (Google Meet, business plans, no regulated customers), and the price after February is a question mark. But the direction is clear: Anthropic and SpaceXAI both want their agents in the call, not in the follow-up email. The winners in meeting AI will be the tools that people trust to write things down correctly, and that trust is earned one corrected whiteboard at a time.

Christopher Ort

Christopher Ort

Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU). He is the author of “The Style Penalty”, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.

Timeline

What happened before

  1. Release

    Claude Haiku 5.5

    1M context · $0.1 / $0.5 per 1M tokens

    support.claude.com (source, opens in a new tab)
  2. Release

    Claude Sonnet 5.5

    1M context · $2 / $10 per 1M tokens

    support.claude.com (source, opens in a new tab)
  3. Release

    Claude Opus 5.5

    1M context · $4 / $20 per 1M tokens

    First model of the Claude 5.5 family; performs at the level of Claude Fable 5.1 on most work and costs 40% less to run than Opus 5.

    anthropic.com (source, opens in a new tab)
  4. Release

    Claude Fable 5.1 & Mythos 5.1

    1M context · $10 / $50 per 1M tokens

    Anthropic's most advanced models for coding and knowledge work. Price/context shown for Claude Fable 5.1 (models overview).

    support.claude.com (source, opens in a new tab)
  5. Release

    Claude Opus 5

    1M context · $5 / $25 per 1M tokens

    support.claude.com (source, opens in a new tab)
Full Claude timeline ›

Editor's picks

  1. AI-Powered Antidetect Browsers Enable Mass Social Media Fraud and Influence Operations
  2. Aokigahara Infostealer Targets AI Tools and Developer Credentials
  3. Yoba malware campaign abuses signed ChatGPT and Claude binaries via DLL sideloading
  4. Prompt Adware in Haiou Jailbreak Bundle Injects Ads into Codex Agent Responses
  5. ARTEX AI Hacking Platform Used in Cybercrime Campaigns