Particularly appreciated by coders, Claude is one of the best known and most used AI chatbots currently. One of its features is that it comes with connectors: add-ons that allow you to link the dialog to third-party services such as Spotify, Uber and Slack.
These connectors include several Google apps and I played with Claude’s Gmail integration. Email is one of the biggest time wasters of my day, and if Claude could save me a few minutes here and there, that would be really helpful.
I was worried about letting an AI run amok in my Gmail inbox, and there are reasons to be cautious, but Claude’s analysis and action worked better than expected. Here’s how you can get started and how AI chatbot helped me.
Log in
There’s obviously a privacy trade-off here: you have to agree to Claude accessing your emails and seeing what you’re doing.
Anthropic says personal data is not used for marketing purposes or to create a profile of its users, although text may be used to train its AI models. If you’re not happy with this arrangement, you can turn it off in Claude’s settings.
There’s also the very understandable fear that Claude will suddenly delete 100 emails behind your back, and that’s another thing I was cautious about. However, I didn’t encounter any problems during my testing, and if you want Claude to take actions on your behalf, you can force him to ask you for confirmation every time.
To connect to Gmail from the Claude web application, click on the icon + (more) in the prompt box, and then choose Connectors > Add a connector and find Google’s messaging platform.
You will need to log in to your Gmail account and confirm the connection. You can then invoke the Gmail connector by referencing “gmail” or “email” in your prompts.
You can also get quick ideas by clicking the button From Gmail button below the dialog box. To start, I asked Claude to analyze my methods of organizing my emails: I like to be tidy and precise when it comes to emails, and the AI was awfully good at spotting how I use labels and the different buckets I sort my emails into (my inbox is a strange mix of work, friends, family, press releases, and general miscellaneous).
Claude also did a good job letting me know which emails I often leave unread (newsletters, social media alerts, and promotions, mainly) and giving me a nudge for emails I haven’t responded to. I also appreciated its recommendations for better optimizing my inbox, with smart suggestions for more labels and filters.
Your inbox can say a lot about you and Claude made me understand pretty quickly. It can even create a personal profile and interactive chart based on your inbox: you can get an overview of the tones and styles you use most often. I’m “highly efficient” and “low maintenance”, so I form an orderly queue and commission the editors.
Email management
Analysis and synthesis are practical and are generally where AI is best – but I also wanted to see if Claude could take action for me. The biggest problem in my inbox is the deluge of press releases, which can reach several hundred per day, all of which need to be organized and ready for review.
While many of them aren’t useful or relevant, some are, and it’s applying this kind of discernment that makes me wary of AI’s (or any type of assistant’s) ability to manage. However, Claude was adept at spotting which emails were press releases and which were from companies or people I knew well.
Better yet, it could apply my “PR” tag to any relevant emails that didn’t already have it, ready for sorting later. If you want, you can confirm each action manually or ask Claude to perform them in batches. Claude was able to do it for me quickly and precisely, which really saved me time.
He even did a decent job of selecting the most interesting press releases from the general pile and summarizing what was new in them. It’s not something I think I’ll give up entirely to AI, but it’s a handy way to quickly see if there’s anything I’ve missed, or to get an overview when I’m pressed for time.
I also liked how Claude could select all the services I had recently subscribed to – an occupational hazard for a technology journalist – and remind me to close them. As far as I can tell, he hasn’t missed much, and what I’ve seen so far has encouraged me to explore what else Claude might be doing in my inbox.
There were occasional missteps, like when Claude told me I needed to respond to a review request email when I had already sent a response, but they were rare. The usual “check that the AI is working” applies here too, but that’s enough for it to end up being credited as an inbox assistant that’s definitely worth keeping around.
Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds.
