Claude AI Can Now Send Gmail Messages Without User Approval, Sparking Privacy Concerns

Claude Can Now Send Gmail Messages, Sometimes on Your Behalf

Anthropic's Claude now has more control over Gmail, allowing its AI to send emails on your behalf. The Claude connector for Google Workspace has been available for over a year to help you manage your Google accounts, but this is the first time it can send an AI-generated message. The tool now lets you enter a prompt to ask Claude to draft, reply to, or forward emails, and you can choose whether to confirm approval of the task before sending or let Claude send without a final check. By default, you'll be asked to approve all messages, with Anthropic saying those on Team and Enterprise plans will see "owners decide whether members can allow these actions to run without asking each time." The feature is now available for everyone on paid Claude plans of all tiers. The upgrade also improves file management in its Google Drive integration by enabling prompts to share, move, or delete files across your cloud storage. Anthropic says it will, by default, ask for approval before each of these actions, much like it does when sending emails. Anthropic confirms it can't do everything with Gmail, saying current limitations mean you can't access attachments directly through the Workspace connector tool. It also says it may struggle to load a large inbox or interact with particularly complex Gmail filters. Claude also can't extract images embedded in Drive files, instead focusing its AI tools on text. The tool also gives you access to your Google Calendar, although there are no changes to the service in this latest update. You can continue to view, create, update, and manage events, as well as set up recurring meetings or manage attendees. Claude's Cowork agentic tools are also now available across all mobile and web interfaces if you have a paid account. Anthropic confirmed the rollout finished on Aug. 18, allowing you to ask Cowork to start a task and then pick up the results on another logged-in device later. It means you can now run a task on your computer and access the results on your smartphone or another less powerful device.

Claude can now send emails in Gmail, even without your approval

Anthropic's Claude AI can now take a huge step in your email inbox, with the ability to not only interact with Gmail, but send emails on your behalf without asking you first. A Claude connector has been available for Google Workspace for quite some time now, offering users the ability to help manage their Gmail inbox, Google Calendar events, and Google Drive management as well. A notable omission on Gmail, though, has been the ability to actually send the email. That's changing now, as Claude can now reply to an email, sending that email without your input and on your behalf. You still have to ask Claude to perform the action, but asking the AI to reply to an email can just send the response sight-unseen. Anthropic explains: Ask Claude to reply to a thread, and it drafts and sends the response. You control when it needs your approval. You get to pick whether or not Claude needs approval before hitting send on an email, but it's a big step forward for what the assistant can do on your behalf in the context of Gmail. On a support page, Anthropic says that asking for approval is the default setting, while also clarifying that Claude can also forward emails as well. Send, reply to, and forward emails from Gmail. By default, Claude asks for your approval before each of these actions. On Team and Enterprise plans, owners decide whether members can allow these actions to run without asking each time. This functionality is only available on paid Claude plans. Would you use it?

Claude can now send Gmail emails -- here's why you might want to test it first

Take a quick trip into Claude's collection of connectors and you'll instantly lock eyes with several recognizable tools catered to everyday use. It's no surprise that Google has the top three slots covered, as its Drive, Gmail and Calendar apps take top billing among its offering of Workspace connectors. At first, the Gmail connector was capable of searching for and finding important emails and summarizing long email threads. But thanks to a recent update, Claude's Gmail connector can actually send, reply to, and forward emails from Gmail without having to leave the chatbot's interface. While this feature sounds like a great way to streamline your workflow, it may be worth testing first before you decide to make it a core part of your daily inbox interactions. Here are more details about what Claude's Gmail connector can do, as well as the many ways the chatbot's Drive and Calendar connectors can assist you. Claude's Gmail connectors can do a whole lot more than before The Gmail connector's primary specialties include the following: * Searching and reading emails by relying on natural language queries. * Drafting emails with proper formatting and message context. * Managing email organization with clear labels and specified message threads. * Sending, replying to, and forwarding emails from Gmail. By default, Claude asks for a user's approval before taking any of those actions. On Claude Team and Enterprise plans, owners decide whether members can allow these actions to run without asking every time. * Listing all the saved drafts that exist in your Gmail account. * Accessing email metadata, including attachment metadata (not actual attachment content). Having Claude send a message via Gmail on your behalf certainly sounds intriguing. But it's certainly worth reminding everyone reading that the consequences that come with an AI making a mistake via hallucination when you permit it to send emails without you reviewing them could be severe. And after a recent report from researchers who found a flaw in Claude for Chrome that could allow rogue extensions to read your data and take actions in your accounts, it's worrying that that sort of extension could potentially ask Claude to send emails without you even knowing. I'm curious if Claude watermarking every word it writes may show up in its Gmail responses as well. It certainly makes all the sense in the world to always have Claude's Gmail connector ask for your approval every time it's ready to send out an email on your behalf. As for what the Drive and Calendar Claude connectors can do, check out their respective official descriptions from the Claude Support page below: * Search and retrieve Google Docs from your Drive. * Share, move, and trash files in Google Drive. By default, Claude asks for your approval before each of these actions. On Team and Enterprise plans, owners decide whether members can allow these actions to run without asking each time. * Look up file metadata and preview directly without searching first. * Read Sheets, Slides, PDFs, images, and MS Office files. * Upload any file type, with optional auto-convert to Google formats. * Create folders. * Add Google Docs directly to chats and projects by pasting URLs or selecting from recent documents. * View file permissions and list recent changes to your Drive. * Save Claude-generated files directly to your Drive (requires code execution and file creation to be enabled). * View events and calendars, including shared calendars you have access to. * Create, update, and delete events with full customization. * Find mutual availability across attendees. * Manage attendee lists and respond to invitations (accept, decline, or tentative). * Set up recurring meetings. Final thoughts Even though I practically use AI for everything, I still haven't gotten comfortable with the idea of copy/pasting an email into it and asking it to draft a reply. I'm even more iffy about allowing a chatbot to have full access to my inbox and be able to send replies, with or without my approval. Claude's Gmail connector is super useful, plus its latest ability to handle your replying, sending and forwarding needs is impressive. But give it a test run first to see if it's truly capable of generating a message that wouldn't make the reader think a chatbot wrote it. Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds. Subscribe to Tom's Guide on YouTube and follow us on TikTok.

Anthropic's Claude can now send Gmail emails without asking first

Would you let AI handle your emails? If the masochist in you says "yes," well, I guess you're now in luck! Anthropic has just updated its Claude connector for Google Workspace to allow full Gmail inbox management. This notably includes the ability for the AI assistant to send and reply to emails without additional user input or approval. Claude Connectors are integrations that connect Anthropic's AI assistant Claude to external apps. As 9to5Google points out, a Claude Connector for Google Workspace has already existed for a while. Along with Google Calendar and Google Drive, this Claude Connector included some access to Gmail. However, this week, Anthropic added a new capability to the connector: Claude can now send and reply to emails without even checking with the user. Claude can also forward emails now without asking for approval too. Claude still needs a human user to ask the AI assistant to draft or reply to an email. But, once Claude writes up the response, it no longer needs to check with the user before sending it. According to Anthropic, users can still control when Claude checks for approval before sending an email. Anthropic also says Claude asks for approval by default. So, Claude users need to change their settings to give the AI permission to hit "send' without asking first. One caveat for free Claude users: If you'd like Claude to send emails on your behalf, you will need to subscribe to a paid Claude plan.

'I would rather use my own head than to let Claude reply': Google Workspace users divided on news Claude can now write and send emails in Gmail for you -- without asking for permission

* Claude can now draft and send messages on your behalf in Gmail * However it can do so without asking for permission, potentially leading to awkward responses * Claude also gets stronger Google Drive access, but says it won't train its AI on your files Anthropic has revealed that Claude's integration with Gmail has taken a major step forward - with the AI now able to draft and send emails on a user's behalf. "Ask Claude to reply to a thread, and it drafts and sends the response. You control when it needs your approval," the company wrote in an update on X. However the news immediately prompted a flood of replies and comments from users worried about the potential implications of having an AI send emails unseen by them. Ask for forgiveness, not permission? Although a Claude connector has been available in Google Workspace for a while, actually sending an email on the user's behalf is a significant step forward, and a potentially troubling one at that. Ultimately, the user will still have to ask Claude to perform the action first, but how it drafts the message, and the content within, has the potential to lead to some serious embarrassment for some users. The tool, which is live now, will only be available to users on paid Claude plans, , and Anthropic later clarified the process in a support page, noting that asking for approval is the default setting, and on Team and Enterprise plans, admins will be able to decide "whether members can allow these actions to run without asking each time". The update will also mean Claude can forward emails, and manage files in Google Drive, helping users track down the information they need with a single command, as well as uploading files, creating folders and add Google Docs directly to chats and projects. "Claude mirrors your existing permissions -- you cannot access information you don't already have access to in Google Workspace," the support page noted, adding that Anthropic would not, "train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private." Users appeared divided on the new tool, with some supporting the launch, and others seemingly very opposed. "sending the email was never the hard part, the hard part is the apology email it sends next," one X user wrote. "I would rather use my own head than to let Claude reply especially responding to my clients," another said, "Don't want Claude hallucinating me into exposing my cost or another client's IP. Claude can apologize but not get your client back. Need to keep our brains working and not letting it totally rot." Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.

Claude can now reply to and send Gmail messages on your behalf

Claude can now send Gmail emails without asking for approval every time Claude is taking another step toward becoming an AI assistant that can actually get things done, rather than simply telling users what to do. Anthropic has expanded Claude's Gmail integration, so the AI can now reply to, send, and forward emails on a user's behalf without requiring approval every time. The capability builds on an existing Claude connector for Google Workspace, which already allowed users to work with Gmail, Google Calendar and Google Drive. Sending an email was the notable missing piece. That changes with the latest update, although users still control whether Claude needs permission before sending messages. Claude can now take Gmail off your hands Users can ask Claude to respond to an email thread, and the AI can draft the response and send it. The important change is that Claude no longer needs to stop and wait for the user to manually approve every outgoing message when the appropriate setting is enabled. Recommended Videos Anthropic says approval remains the default. Users can choose whether Claude needs confirmation before sending emails, while Team and Enterprise administrators can determine whether members are allowed to let these actions happen without repeated approval. The feature is available only on paid Claude plans. Claude can also forward emails, expanding the feature beyond simple replies. That turns the Gmail integration into something closer to an assistant operating inside the inbox rather than an AI that merely summarizes messages or writes suggested responses. The distinction matters because sending an email is fundamentally different from generating one. A chatbot can produce a perfectly written reply and leave the final decision to the user. An agent that can actually press Send crosses into taking action on the user's behalf. The useful part is also the risky part For people dealing with repetitive email, the change could save considerable time. Routine replies, follow-ups, and forwarding messages are precisely the sort of tasks an AI agent can handle without much human involvement. Giving an AI permission to send messages also introduces an obvious question: what happens when Claude misunderstands the context? An incorrectly worded draft is easy to fix when it is sitting in the compose window. A message that has already been sent is another matter. Anthropic's approval system provides a safety valve, but the decision to remove that checkpoint puts more responsibility on users and, for workplace accounts, administrators. The development also signals where AI assistants are heading. The goal is increasingly not just to answer questions but to interact with the services people already use and complete tasks inside them. Claude's Gmail capabilities are currently limited to paid plans, with approval settings varying according to the account type. For users willing to give the assistant more autonomy, email could become one of the first everyday tasks where AI moves from suggesting an action to actually carrying it out.

I Let Claude Answer My Emails for Me, and Here's How It Went

It adds to the Gmail searching and summarizing tools Claude already had. If AI is going to take all of our jobs, the least it can do is make those jobs a little easier while we still have them, and email admin is one of the biggest time sinks I've got in my daily routine. I'm spending hours a week reading and responding to emails when I really need that time to get on with writing about new Pixels or Mac apps. My interest was piqued then by the news that the Claude AI chatbot can now respond to and send emails in a connected Gmail account-and without your specific approval, if you're happy to let it work automatically. Claude has been able to plug into Gmail accounts for a while, so you could already get it to read through and summarize incoming messages -- but any email drafting had to be done in the Claude bot and copied over. Now the AI is able to compose and send responses inside Gmail without you having to switch over to the Google email client yourself. Could this free up some more time in my day? Is it really wise to hand over emailing duties to an AI bot? I gave it a try to assess how it might impact my productivity (and sanity). How to connect Claude to your gmail account You need a paid Claude plan for this at the moment, so you're going to have to be on the $20-a-month Pro plan or something higher. To connect your Gmail account if you haven't already, open Claude on the web and click your profile picture (bottom left), then select Settings > Connectors and find Gmail. (If you don't see your profile picture, click the menu button, top left.) To do something in Gmail, you just need to mention it in a prompt. If you're not quite ready to do some drafting and sending, try a prompt like "who's emailed me most today" or "summarize the emails I've received this week." Claude rummages through your Gmail account and delivers what you asked for as a response. When you're ready to start sending, you can be pretty informal and ambiguous with your prompt. Saying "reply to my last unread email," "reply to David Nield," and "reply to the Story edits thread" will all work in Claude. However, the more precise you can be -- with a specific email address, for instance -- the better, in terms of avoiding mistakes. If you say "send an email to Dave" and Claude finds three people with that name, it will ask who you mean. However, if it finds the wrong Dave and misses the other two for whatever reason (maybe due to formatting or email address construction), it will make the incorrect pick and not tell you about it. So, be as precise as you can. Next, you tell Claude what to say: You can dictate the message word for word, or tell Claude to get creative and use its imagination, or do a mix of the two. This works the same as any other text prompt -- supply as much or as little direction as you want regarding email content, style, intention, and other characteristics. You'll be relieved to hear that automatic sending is off by default. If you go back to Settings > Connectors, you can click Gmail to set permissions. Different actions, like searching through your inbox, sending emails, and editing labels, can be set to one of three different options: Never allow, always allow, or always ask for permission. Here's what happened when I let Claude manage my inbox I took the risk and gave Claude permission to send emails automatically without approving each draft and got to work. I did consider getting in touch with the Lifehacker editors, but keen to stay on the roster here and avoid any hallucinated misunderstandings, I decided to have an email conversation with myself, via a secondary email address. Claude actually works really well for getting around your Gmail inbox: It understands labels, dates, contacts, subject headers, themes, and nuance. It easily identified "the email I've just sent myself from my Proton account" without me having to open up Gmail, and I told it to reply -- saying that it should agree to a meeting and talk about the weather. One immediate problem: It signed off my email with "cheers,, something I would never say outside of specific scenarios involving bars and clinking glasses. I don't think I've ever used that in an email, but evidently a lot of people in Claude's training data have, which is why it was included. Be aware that Claude may not catch your default tone and personal nuances when you let it compose your messages. The rest of the email was fine, if a little generic: I agreed to a meeting (with myself), and mentioned the weather (a standard British conversation topic). I then repeated the process several times, giving Claude different levels of freedom when it came to composing message replies. On a technical level, it's all quite impressive. Claude can accurately pick up and transfer what's in an email thread and compose replies as instructed. I told it to generate a message summarizing my work for the week (via its Google Drive access), and to add a question about a weekend soccer match, and it did both with aplomb. We know AI makes mistakes, but I didn't see any in my testing. As clever as this is, though, the biggest issue is that I can't really see myself using it. To begin with, these emails aren't written in my voice or style, and I'd be continually worried that Claude was about to make a terrible error somewhere (maybe in misinterpreting an incoming email, or getting something wrong in an outgoing one). Another concern is where all this is heading: AIs emailing other AIs, into infinity? I already suspect a lot of the emails I get are crafted by chatbots, which immediately devalues them. If I'm going to communicate with someone, I feel I owe it to them to actually put together the message myself. While I think I'll keep Claude's Gmail connector around to search and summarize emails, the sending and drafting features are getting turned off for now.

Claude Can Now Take Actions For You in Gmail, Google Drive

* Claude can manage files for users in Google Drive * Users can add the Google Workspace connectors in the app * The connectors are available to all users Claude users have had the option to connect their Google Workspace apps, including Gmail, Google Calendar, and Google Drive, for a while now. However, the connectors missed a few basic abilities. Now, Anthropic has updated the Google Workspace connectors for its AI chatbot, Claude. The update brings the ability to allow Claude to reply to email threads, send emails, and do more in Gmail. On top of this, with the updated Google Workspace connectors, Claude can now manage files and folders in Google Drive for users. This adds to the existing features that are offered with Google Drive, Gmail, and Google Calendar connectors in Claude. Claude AI's Google Workspace Connectors Features, Capabilities In a post on X, the US-based AI giant Anthropic announced that Claude can now take more actions in Gmail and Google Drive for users, using the updated Google Workspace connectors. The tech firm said that Claude can now send emails in Gmail and manage files in Google Drive. Further, with the Google Workspace connectors, the AI agent can reply to email threads after drafting the email and sending it after your approval. The company has also updated it support page to provide more details on the added capabilities. Anthropic says that Claude will ask for approval each time before taking any action, including sending, replying to, and forwarding emails, on a user's behalf. Similarly, organisations on Team and Enterprise plans will have the ability to allow the aforementioned actions to be executed without prior approval each time. Anthropic says that the Google Workspace connectors in Claude are available to all users on Claude and Claude Desktop. However, Team and Enterprise plan owners will have to enable the ability to add these connectors. As previously mentioned, this adds to the list of abilities that the Google Workspace connectors previously offered in Claude. With the connectors, the AI chatbot can access email metadata, manage email organisation with labels and threads, and list saved drafts within the Claude chat window. In Google Drive, Claude can search and retrieve documents, share, move, and delete files, look for file metadata, read documents, create folders, and directly save the Claude-generated files in Google Drive. Similarly, with the Google Calendar connector, Claude can view events, create events, find mutual availability, set up meetings, and manage attendee lists.

How to let Claude send and reply to Gmail emails on your behalf

Users can connect Gmail and ask Claude to draft or send replies. Anthropic's Claude can now do more than read and search through your Gmail inbox. With the Google Workspace connector enabled, the AI assistant can draft and send replies, forward emails and handle certain Gmail actions on your behalf. By default, Claude asks for your approval before sending an email. However, depending on your plan and account settings, you can allow certain actions to happen without requiring confirmation every time. How to connect Gmail to Claude Right before you ask Anthropic's AI chatbot to manage the emails, you will have to connect your Google account. 1. Open Claude and sign in to your account. 2. Go to the Connectors section. 3. Find and select Google Workspace. 4. Tap on Gmail and respond to the options coming on your screen. 5. Sign in to your Google account and grant Claude the required permissions. 6. Once connected, return to Claude and start a new conversation. 7. You can similarly connect Google Drive and Google Calendar if you want Claude to work with those services. Also read: Motorola Signature price drop: Save over Rs 5,800, here is how How to ask Claude to reply to an email Now comes the main part. Once you connect Gmail, you can ask Claude to respond to an existing conversation using a natural-language prompt. 1. Go to Claude conversation 2. Now ask Claude to find the email or thread 3. Tell it what you want the response to say. 4. Claude will then prepare the response based on the email context 5. Review that draft once the chatbot asks for approval 6. Approve the action to send the email through Gmail. 7. You can also ask Claude to forward an email to a specific recipient. Also read: Samsung Galaxy A35 deal: Get over Rs 14000 discount, here is how Can Claude send emails without approval? The answer to this question is yes but only if approval is enabled by default. Claude normally asks you to confirm before sending, replying to forwarding messages. Whether you can disable this confirmation will actually depend on your account and plan. If you have the Team and Enterprise accounts, admin can determine whether members are allowed to perform these actions without confirmation. And most importantly, now that Claude can communicate externally on your behalf, I would advise you to keep approval enabled if you want to review the AI generated emails before they are sent.