And I keep thinking: why isn't everyone doing this?
The entire AI coding conversation is about building new apps from scratch. Cool. But I don't need a new app. Most people spend their workday inside apps they didn't choose: Jira, Salesforce, Workday, ServiceNow, etc. These tools are not going anywhere. My company chose them in 2019 and they're entrenched until at least 2029.
Chrome extensions just reads what's already in the DOM and augments it.
Is there a fundamental reason this can't work at scale that I'm not seeing? Why isn't Claude's Chrome extension catching more attention?
The greatest danger of the current time is that the likes of Salesforce and LinkedIn who have something interesting behind an API or web site try to lock down access so instead of using competitive high-quality AI agents we're stuck with the brain damaged AI agents they want to force on us.
I have an "image sorter" that ingests image galleries, it used to use a bookmarklet that cued a webcrawler but after a decade of having my time as a user wasted clicking on those Cloudflare thingies I finally had it get in the way of my webcrawler.
I was talking about options w/ Junie and it suggested, "why not write a browser extension?" and I'm like "is that hard?" and it says "no" and 20 minutes later I have a prototype browser extension.
So that plug-in you're talking about where an AI can see directly into your browser is another option, another is vibe-coding a custom browser extension. I think it was always pretty easy to write a browser extension but I had I done it myself my usual scholarly way I'd spend a few hours reading documentation before I started coding and never realized just how simple it is... Just the way people are discovering web crawlers and API integrations are easier than they thought.