But do you (or MSFT) trust it to do that correctly, consistently, and handle failure modes (what happens when the meaning of that button/screen changes)?

I agree, an assistant would be fantastic in my life, but LLMs aren't AGI. They can not reason about my intentions, don't ask clarifing questions (bring back ELIZA), and handle state in an interesting way (are there designs out there that automatically prune/compress context?).

>improve things they are already doing repeatedly. For example, I click the same button in Epic every day because Epic can't remove a tab. Maybe Copilot could learn that I do this and just...do it for me?

You could solve that issue (and probably lot's of similar issues) with something like Auto Hotkey. Seems like extreme overkill to have an autonomous agent watch everything you do, so it might possibly click a button.

Auto Hotkey doesn't work well for Epic manipulation because Epic runs inside of a Citrix Virtual Machine. You can't just read Window information and navigate that way. You'd have to have some sort of on-screen OCR to detect whether Epic is open, has focus, and is showing the tab that I want to close. Also, the tab itself can't be closed...I'm just clicking on the tab next to it.

Doable in Autohotkey. You can take a screenshot of what to look for, and tell AutoHotKey to navigate the mouse to it on the screen if it finds it.

I've done similar things.

Do you stop to think of the wastage of resources that is having an auto OCR of the screen and a LLM to simply close a tab.

And in an ideal world, one could report this as a bug or improvement and get it fixed for every single user without them needing to do anything at all.

Well, it isn't every user. We use a version of Epic called Epic Radiant. It's designed for radiologists. The tab that always opens is the radiologist worklist. The thing is, we don't use that worklist for procedures (I'm an interventional radiologist). So that tab is always there, always opens first, and always shows an empty list. It can't be removed in the Radiant version of Epic.

I'm sure you have, but try be bringing that up to Epic, not introducing AI slop and Data gathering into HIPPA workflows.

But why would Epic spend money improving or fixing their software? If they spend money developing their product then they can't spend that money on their adult playground of a campus!

I think what people want in the long term is truly malleable software: https://manuel.kiessling.net/2025/11/04/what-if-software-shi...

I can’t find any use case for Copilot at all, and I frequently “sell” people Microsoft 365. (I don’t earn a commission; I just help them sign up for it.) I cannot come up with a reason anyone needs Copilot.

Meanwhile I spent 3-4 hours working with a client yesterday using Dreamhost’s free AI tools to get them up and running with a website quickly whilst I configured Microsoft 365, Cloudflare, email and so forth for them.

> Like, Copilot could watch my daily habits and offer automation for recurring things.

We're working on it at https://github.com/openadaptai/openadapt.

> Copilot could watch my daily habits and offer automation for recurring things

Pretty sure the advertising department already watches you and helpfully suggests things that you need to buy.

I actually would like it to improve my writing. Problem is LLMs aren't particularly good for this (yet).

If you use a LLM for writing, then you aren't writing anything.

Your comment is very knee jerk.

I said "improve", not "write". As in pre-LLM days you'd give what you wrote to someone else to review and give feedback.