Putting Gemini to Work in Chrome

You know, the whole "faster horse" argument.

I dread having to log in to these systems and waste hours achieving the simplest tasks.

This is what I'm using Claude for. E.g. I log in to AppStore connect, tell it what I need (3 subscription tiers), it will do all the clicking and editing and Apple's stupid UI, then I will ask it to create a summary for RevenueCat, and use another Claude session in there to click all the buttons to configure based on what just happened in Appstore connect.

Or configuring S3 buckets or whatnot.

Of course the single biggest thing my browser can do to help me is blocking ads, which means it's curious to see this just after Google killed adblock in chrome.

Also for things like locating a product available to pick up in a nearby store, it’s crazy how often Google fails at this particular task.

Sounds like a contrived situation, but there's a surprising amount of "thought leader" CEOs out there who make completely nonsensical decisions under the banner of "saving costs and automating things".

(Real-world example I know of) company pays for cheapest tier they can find of Gemini, tell everyone to use it. But won't pay for Asana seats, so every user in your 100-person startup is a guest, and can't use the connector in any AI app to TRULY do useful task management with AI.

Having some better access to AI in the browser would pave over that pain for someone who currently doesn't want to spend their own money on something like Claude for Cowork and the Chrome extension to drive the browser, or open a terminal to have Claude Code do it.

Examples: using my budgeting app directly to figure out why some forecasting event went wrong, or helping me correlate SOC2 tickets with GitHub pull requests and flagging all that are older than $date.

It’s surprisingly convenient for a narrow set of tasks.

However, Gemini in Chrome requires you to allow them to use your data to improve their model, which I won't consent to. Google workspace account seems exempt so I plan to try it out there.

These feels on par with Microsoft's push to shove Copilot down everyone's neck at every step possible whether we like/need it or not

Like the first example in the demo carousel (the Y2K party) starts from a photo and a prompt of roughly "buy the props needed for replicating this photo from Etsy". It first analyzes the image in the current tab, identifies a bunch of things to buy, searches for them on Etsy, customizes the orders, adds them to the shopping basket, and then asks for a confirmation to actually send an order.

The second one auto-fills a form with a couple of dozen fields from the data that's in a pdf in another tab. (And in the fiction of a demo, presumably a pdf that's you already had around, not one that you made just for the purposes of using it to auto-fill the form.)

I'm not the target market for this: automating a browser with my credentials is just too scary, but I can certainly see the utility. There's a huge amount of tasks taking a minute or two are not worth creating bespoke automation for but that are also pretty mechanical processes.

But for regular browsing? I don't see the point.