Feedback Please: Trying to create an automatically self improving AI planner?

Anyone interested in a calendar app that automatically learns about you based on your data in order to make you more productivity and gives guidance to help maximize time/schedule while also getting rids of bad habits and routines?

I would love to hear any of your feedback, advice, & questions! :grinning:

With Kindness, :grin:
-Marquis B.

1 Like

Sure! Does it run on Android, or is it a Progressive Web App?

1 Like

Yes, I would be interested! I am making a working schedule everyday, I grade my activities (with flow scores) and conclude if, and why I deviated from my daily planning. I found some interesting things which might be incorporated into you calendar app.

Main findings:

  • I deviate from my schedule when I am working at home
  • I deviate from my schedule if I want to finish something
  • I deviate from my schedule whenever my phone is buzzing
  • I deviate from my schedule when I get (seemingly) important e-mails or emails that I am eager to answer
  • I deviate form my schedule when I am scheduled to write e-mails (these often take longer than expected). But I am also a person who learns based on data, thus I schedule more time for them now (haha).
  • My flow is mostly determined on project (and duration of the project), not on time of the day

These are things I learned just by tracking it, I haven’t proven them statistically.
Hope you can work with my feedback. Would be happy to discuss more about it :slight_smile:

1 Like

I currently gather my own daily day - manually. I am also involved with the team that is creating SkedPal and I am recognizing that there are opportunities to gather all sorts of new data via this programme and others like it called auto-schedulers.

Because it’s a programme that produces a calendar run daily, in the future it should offer rich opportunities to gather the kind of data mentioned by justintimmer.

At the moment, Google Goals and Todoist Smart Schedule promise to build a schedule for you that’s based on your personal history, plus that of others. However, I haven’t seen too many actual success stories, which makes me think that they are trying to do too much at once.

In my opinion, in the beginning, users just want a way to auto-schedule themselves accurately and the best information to use isn’t based on machine learning, but an understanding of their own behaviour. However, as time goes on, an app could certainly include this kind of information.

I think it would supplement user input on each task, rather than replace it. If the kind of data that justintimmer describes were available, then users could build higher quality schedules because they are using better-quality feedback.

I hope this helps,



Hey @Dan_Dascalescu

I am leaning more towards a Progressive Web App first based on your article I had a chance to read, thank you so much for that key piece of information. Would you say a company like Evernote uses a progressive web app (PWA) method?

Hey @justintimmer could you tell me what our flow scores it sound very interesting? Also your findings is great I have found the same issues with my activities; the must important one: [quote=“justintimmer, post:3, topic:3251”]
I deviate from my schedule whenever my phone is buzzing

one of my findings also.

Hey @TheNotifiedSelf

This input was needed and really opened my eyes to a new view point


Yes ,Sure i am also interested in to learn about this type app which is guide you and remind you with your scheduling works .How it will work and how it will benefited to us , i want to know.please guide us.


1 Like

Yes, apparently we decided one day that we stop whatever we are doing whenever our phone is ringing, haha. First our phone’s only rung when something was really urgent, and we learned ourselves to answer it quickly.

About Flow: I tried to find out how Flow works and to verify Csikszentmihalyi’s flow model. Thus, I tracked my feeling of Flow, the challenges, and abilities I have per project. After completing a project/task I gave these factors a number (1-10). I had done statistical and thorough analysis yet. But I already found out that the flow-model is in a broad sense quite right. However, flow is a more complex, it is a iterative system but is dependent on what kind of task you are performing. I think I’ll need to blog about the experiment to explain the full story.

1 Like

I too use a app on my Android Phone. It generally does below stuff

  1. Track your daily activities( Walk, Run, Rest etc)
  2. Alerts you when to drink water
  3. Tracks your weight changes

Few things I miss which you might include or already have

Gives you instant notification of any bad food habits
Information on constituents of each food item(protein, Carbohydrate, Fat etc) by just entering their details

So if your AI based app is so helpful, then surely will be interested in it.