Aye - Your teachable AI intern for everyday browser work
by•
Aye is a Chromium-based AI browser for macOS and Windows that gives web work a teachable AI intern. It reads visible pages, plans steps, and works through normal browser actions: clicking, typing, scrolling, switching tabs, and checking results. Summarize pages, research across tabs, draft replies, and automate repeatable workflows. Turn recurring tasks into reusable skills, separate accounts with profiles, and stay in control with reviewable progress and approval for sensitive steps.
Replies
Hi Product Hunt! I'm excited to share Aye, an AI browser for macOS and Windows built by Zhonglin Liu.
Browser work often starts with a simple goal but turns into a long chain of reading, comparing, clicking, and rewriting. Aye helps carry that work forward through visible, reviewable actions on real websites.
It can summarize and translate pages, research across tabs, draft content, and automate repeatable workflows. Recurring tasks can be turned into reusable skills, while sensitive steps stay under your approval.
I'd love to hear what browser workflows you would want Aye to handle.
@siyan_chen1 I've hit the wall with browser agents on the 5% of edge cases that break a recorded flow. When a layout changes or a step fails, does Aye stop and ask or improvise and risk the wrong action? And how much correction before a task actually sticks?
The profiles feature is great for keeping things separate, but I'd love to see some kind of shared library or way to export a skill I built on one profile and use it on another. Right now if I make a really useful workflow on my personal profile, I basically have to rebuild it from scratch on my work profile. A simple import/export button for skills would save a lot of time and honestly would probably get me using Aye way more across both accounts.
I like the idea of teaching the browser instead of repeating tasks every day. How do skills improve after mistakes? Maybe showing learning history could users trust workflow more.
Browser agents tend to hold up in the demo and fall apart by run 50. Teaching flows helps, but recovery is the test, what happens when the DOM shifts or an auth step appears mid-task. How does Aye handle a flow that partially fails halfway through? Rooting for this category to mature.
'teachable' is the right word, most browser agents just replay. when i correct it once, does that generalize or only fix the exact flow i taught?
the approval step for sensitive actions is genuinely thoughtful, you know most browser agents just bulldoze through stuff without checking. feels like the team actually thought about trust before shipping.