Skip to content
NEW Claude Meetings is INSANE! 🤯 artwork

NEW Claude Meetings is INSANE! 🤯

AI News Today | Julian Goldie Podcast

November 14, 2026

NEW Claude Meetings is INSANE! 🤯

Speakers Julian Goldie

TopicsMarketingBusiness

Julian Goldie (0:00)

Claude can now join your video calls. Anthropic just launched Claude Meetings, and it puts Claude inside your Google Meet as a real participant, with its own tile next to everyone else. You talk, it listens. And when somebody says, Claude, make a doc, it builds the doc right there, while the call is still going. Docs, whiteboards, and slides, all made live, all saved to one page when the call ends. It answers questions in the chat. It can even use your connected tools, like sending a message to your team in Slack after it asks you first. So the proposal, the plan, and the follow up are finished before anyone says goodbye.

In this video, I'll show you exactly how it works, who can use it right now, and how an online store and an agency would use it on the calls they already have every week. And stay with me, because there's one setting about outside guests that every agency owner needs to know before they add Claude to a client call.

Let me start with what actually happened. On the 12th of November, Anthropic announced Claude Meetings. It's in beta, which means it's new and still being improved. It's rolling out on Claude's team and enterprise plans, in Claude on the web and in the Claude desktop app. Right now, it works with Google Meet. Anthropic says other video platforms are coming later.

Here's the simple version of what it does. You open Claude, you click on Meetings, you connect to your Google Calendar, you pick a meeting, and you click Add Claude. That's the whole setup. When the meeting starts, Claude joins the call just like a person would. It shows up as its own tile in the grid, so everyone can see it's there. And that tile is live. It shows what Claude is doing at that moment, so you can glance over and see if it's listening, thinking, or building something. When it joins, it also posts a note in the Meet chat so everyone on the call knows it's in the room.

Now, if you don't want to add it by hand every time, there's an auto-join setting. You can tell Claude to join all of your meetings, or all of your meetings accept your one-on-ones. That second option is handy because a lot of people want help on team calls and client calls, but not on a private chat with one person. And one important thing from Anthropics' own help page. Before you add Claude or switch on auto-join, make sure everyone on the call is okay with being transcribed. That's the polite move, and it's the right move.

So what can you actually do once Claude is in the call? There are three things, and each one is bigger than the last. The first one is questions. You just say Claude and then ask your question out loud, or you type it in the Meet chat. By default, Claude answers in writing, in the chat, so it never talks over anyone.

Think about how often a call stops dead because nobody remembers something. What did we agree with this client last month? What's our return policy again? Which product sold best in October? Now you ask, and the answer appears in the chat while the conversation keeps moving.

The second one is the big one. Claude builds things with you, live, while you're talking. You say Claude, make a doc, or Claude, make a whiteboard, and it starts building. Docs, whiteboards, and slides are all supported. Anyone on your team can ask for one. You can make as many as you want in a single call, and every single thing it makes gets attached to that meeting's own page, so nothing gets lost in a random folder.

This is the part that changes how a call feels. Normally, a meeting is talking. The real work happens afterwards, when somebody sits down alone and tries to remember what everyone said. With Claude Meetings, the work happens during the talking.

The third one is your tools. Claude can use the tools you've already connected to Claude during the call. Anthropic's own example is sending a Slack message, and it's careful about it. It uses each person's tools only with that person's permission. The first time, it asks you, and once you say yes, that yes applies going forward. If someone asks out loud, Claude checks who's speaking before it acts, every time for now. So nobody on the call can quietly send a message from your account.

And when the call ends, here's what you get. Every meeting has its own meeting page. On that page, you get the notes with the summary and the action items. You get the full transcript, and you get everything Claude made during the call. The docs, the whiteboards, the slides. Everyone from your company who was on the invite gets a recap email with a link to that page. They can read the notes and they can edit what Claude made. And here's a small detail that matters a lot. Later on, in a normal Claude chat, you can ask Claude about past meetings you have access to. So next Tuesday, you can just ask, what did we decide about the holiday launch? And Claude goes and finds it.

Read the other 11 minutes of this episode here.

$15 gets you this episode and 99 more. Credits never expire. After checkout, one link brings you back here to read it.

Not what you expected? Full refund within 14 days.

Thousands of transcripts fetched by people building searchable podcast archives

Fetch transcripts with code

The same credits work from a script or an AI agent. The demo key returns a sample episode in full, no card needed:

request
curl -H "x-api-key: pt_demo" \
  https://spoken.md/transcripts/1000651996090

Markdown with the speakers named, for your notes, your knowledge base, or anything that makes HTTP calls.

From $0.10 per transcript. No subscription. Credits never expire. Prices exclude VAT, added at checkout for EU customers. Not what you expected? Email us within 14 days with 20 or fewer credits used and we refund the pack in full.

Using your own key:

request
curl -H "x-api-key: YOUR_KEY" \
  https://spoken.md/transcripts/1000801829206