nxt - Talk to your to do list and get what's next
nxt is the AI task manager you talk to like a human assistant.
Brain-dump your thoughts in plain language - nxt reads between the lines, extracts tasks, infers priorities, and files everything automatically. It understands what you mean, not just what you say. nxt learns your personal context, so your tasks flex around your life.
When you're ready to act, nxt cuts through the noise and gives you one clear task, one reason why. No scrolling, no paralysis, no overwhelming list to wade through.

Replies
I use just Apple notes for my to do list but just speaking what I want to add when I want to add is a neat idea. Cool that it learns your habits!
Voquill
This looks really interesting. How easy is it to correct when it gets a task or priority wrong? Good luck and congrats!
Magic Bookshelf - AI Stories
@henry_habib Thank you! Really easy - you can go into any task and manually tweak anything it got wrong: title, description, priority, scheduling. And we're working on making that conversational too, so you'll be able to just tell nxt what to fix rather than editing manually.
How does it actually decide what to surface as "the one clear task" when several things feel equally urgent?
Magic Bookshelf - AI Stories
@sedanurnnjz It weighs up a bunch of signals at once: the time of day, your energy patterns, how long the task is likely to take, and everything it knows about your context. Two tasks might look equally urgent on paper, but if you've got a dentist appointment in 45 minutes, or the school run, nxt knows this isn't the moment to start the thing that needs two hours of deep focus - it'll surface a quicker win instead.
In practice it gets better the more you use it, as it builds a clearer picture of how you work. Would love to hear if the reasoning feels right once you try it!
Magic Bookshelf - AI Stories
@shubham4real nxt stores context as you go, so if you said something like "the marketing summary points need to be ready for the 10am meeting Friday, and my boss Jeff has asked me to look at last months figures to pull out the key changes" - this would turn into two tasks, one with a set deadline pre that 10am meeting) and one without, and it would also add a context entry along the lines of "Boss is called Jeff". For priorities will then work with that info - it knows a deadline for one, and it knows your boss asked you about the other one and can factor that in. It also learns from behaviour: if a task gets snoozed every time it's surfaced at a particular moment, nxt takes note. Same the other way: patterns around when things actually get done stick over time.
No clarifying questions upfront (yet!), so we recommend giving it as much context as you can when doing the verbal brain dump. You always have full visibility over the context it's working with, so it's never a black box. You can see exactly what it knows and correct it if it's off.
How does nxt actually handle the "between the lines" part in practice - does it just run everything through an LLM each time, or is there some kind of learned model on your device that gets smarter as you use it more?
Magic Bookshelf - AI Stories
@enaypbab Great question! The best analogy is ChatGPT's memory feature. As you use nxt, it stores discrete facts about you and your life, and hands those to the alongside your tasks to the recommendation engine. So it's not getting smarter in a model sense, it's getting smarter because it knows more about you.
You have full visibility and control over exactly what it's stored - you can see every fact it's working with and edit or remove anything that's wrong or out of date, or even add extra context directly.
the "one clear task, one reason why" approach is genuinely smart - too many task apps drown you in options when your brain just wants a single next move. love that it files everything automatically instead of making you play secretary.
Magic Bookshelf - AI Stories
@grselgrsuwhwo Thank you so much!
How does nxt handle tasks when you mention something ambiguous like "next Tuesday" without specifying a time zone — does it learn mine or default to device settings?
Magic Bookshelf - AI Stories
@evketgkb4 nxt picks up your timezone automatically on setup so that side just works. The more interesting scheduling magic is what it does with natural language - things like "pay the window cleaner the first Monday of each month" or "dance class at 5pm every other Thursday starting this week" just get handled.
Nice approach. Does it connect to existing calendars or does it work as a standalone task manager?
Magic Bookshelf - AI Stories
@dhiraj_patel5 Standalone for now, but calendar integration is on the roadmap! In the meantime nxt works around your schedule using the context and availability windows you set directly in the app.
Honestly the one-task-at-a-time view is the part that got me, it stopped me from staring at a list and actually doing something. Also weirdly nice that it picked up priority just from me rambling about my day.
Magic Bookshelf - AI Stories
@ezelrikliahcg The rambling-to-tasks thing never gets old for me either, it still feels a bit magic every time. Would love to hear what you think as you use it more!
The "one task at a time" approach is such a thoughtful cut against the typical productivity app bloat. Feels like the team actually sat with the problem instead of just stacking features.