[owlmirror]

- "summarize the discussions on hacker news of last week based on what I would find interesting".

- "Plan my summer vacation with my family, suggest different options"

- "Look at my household budget and find ways to be more frugal."

There are thousands of things I can think of when it comes to how an agentic OS would work better than the current Screen Keyboard paradigm. I mean all these things I could now do with Claude or Codex and some of these things I already do with these tools.

[MeetingsBrowser]

Neither of those really have to do with the OS though. For example:

> Plan my summer vacation with my family, suggest different options

What part of this does an agentic OS help with? My OS doesn't know my travel preferences, family size, work schedule, etc.

These are more appropriate tasks for a smart assistant.

What specifically does an agentic OS UX look like beyond giving claude access to local files and a browser?

[owlmirror]

>What specifically does an agentic OS UX look like beyond giving claude access to local files and a browser?

Providing the structure of a unified framework: APIs, safeguards, routing to the appropriate model or pipeline, and controlled access to devices and data. The capability is already there. What’s missing is a sane permission system that operates at the level of intent. Having used OpenClaw, that’s IMO the missing piece. It’s a fun experience, but in its current state I would not trust it to autonomously run any meaningful part of my life.

UX-wise, chat is kind of a crutch. It’s slow and inherently limiting. I imagine something closer to a natural, ongoing conversation paired with an execution layer: some sort of approval or review dashboard where planned actions are ready for approval or returned for refinment before they happen. Probably with a conservative moderator agent in the loop that flags things based on preferences and hard-coded policies.

Calling it an OS isn’t accurate, I agree. But that's how people will perceive it. Most people already think of the application layer on Android as "the OS," not the kernel or drivers. This will be the first-class interface on your device, so that’s what it gets called. It doesn’t mean browsers or dedicated applications go away.

Three years ago I would not have thought the IDE would stop being the application I spend most of my time in. Now it’s mostly a passive code viewer and Git browser.

Compare that to everyday workflows. Researching anything still feels incredibly antiquated. Buying a phone, planning a vacation, comparing options means opening dozens of tabs, copy-pasting specs or prices into spreadsheets, reading through fine print, dealing with low-quality or honestly untrustworthy reviews, checking distances manually on maps. It’s boring and tedious work.

Meanwhile, in a professional life, these systems already behave like a team of secretaries: always available, reasonably competent, and scalable. Not perfect, but easily good enough to offload a huge amount of cognitive overhead.

[malfist]

I don't want those. Why read books when you can have an ai summarize it in two paragraphs for you? Because I want to know and learn and enrich myself.

[xvector]

Sure but most people just want to get shit done. If you don't want it you can always take the long meandering path, no one is stopping that.

[malfist]

What I'm trying to say is the long path is "get shit done". No work is completed by reading AI summaries of informative content. Its just productivity porn

[xvector]

Of course shit gets done. Who thinks AI is just summaries? That's so 2024. Agents are a thing.

[dijksterhuis]

> I mean all these things I could now do with Claude or Codex and some of these things I already do with these tools.

huh? ... this reads to me like you don't need an "agentic" OS to do the things you'd want to use an "agentic" OS for..?

like... it seems you just don't want a keyboard to do the same things you've already been doing? ... is that the crux of it?

[JohnFen]

None of those need to, or should, be done at the OS level.