Is there an app that notices when my day is slipping and suggests one next step?

PursueUpdated 17 October 20266 sources

Short answer

Tre-Up, an iOS app in development, is being built for exactly that, and it is not released yet: its AI, Pursue, is designed to notice when your focus or energy shifts and to answer with one small next step, one question, or nothing. Until it ships, your phone's focus modes and scheduled notification summaries cover part of the job.

01What Tre-Up is

Tre-Up is an iOS app in development, built by its founder in Istanbul, Türkiye; it is not yet incorporated. Pursue is the AI inside it. The idea is simple to say and hard to build: notice the moment a day starts to slip, and answer with one small step you can take now, a single question when Pursue doesn't know enough, or nothing at all when nothing needs to change.

It is not released, and we make no claim yet that it works. In Tre-Up's first test with real people, the main question the next day, for invited participants, is: did you take the step?

02The research behind the design

The design rests on published research, summarised across these notes. Support should adapt to the moment, and giving nothing is a real option[1]. Opening an app is not the same as benefiting from it[2]. Fewer, grouped signals beat a constant stream[3]. Offers land better than orders[4]. A system's confidence has to be earned, not displayed[5], and a new user should be asked, not guessed about[6].

03What you can use today

Until Tre-Up is available, the built-in tools on your phone do part of the job: focus modes to decide who can reach you, and a scheduled summary to batch the rest. They don't notice when your day shifts, and they don't suggest a next step, but they reduce the noise that makes a day slip in the first place.

Something to try today

Set a focus mode for your most important hour tomorrow, and when it ends, write down the single next step for whatever you were doing.

Pursue

How Tre-Up approaches this

Tre-Up does not sell your data, not personal, not anonymous, not pooled. Invitations to the early version go out in small groups.

Tre-Up is an iOS app in development. Pursue is the AI inside it. This note describes research and design intent, not results from the app. Nothing here is medical advice.

Sources

Summaries are written in our own words from each source's abstract, public record or official text. Follow the link to read the original. How we write these notes

  1. 1.Nahum-Shani I, Smith SN, Spring BJ, Collins LM, Witkiewitz K, Tewari A, Murphy SA (2018). Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support. Annals of Behavioral Medicine 52(6):446–462.University of Michigan · Northwestern University · Pennsylvania State University · University of New MexicoOur summarydoi:10.1007/s12160-016-9830-8
  2. 2.Golbus JR, Dorsch MP, Chen Y, Basu T, Luff E, Klasnja P, Newman MW, Skolarus LE, Dempsey W, Nallamothu BK (2026). Impact of Push Notifications on Physical Activity and Sodium Intake Among Patients with Hypertension: Microrandomized Trial of a Just-in-Time Adaptive Intervention. Journal of Medical Internet Research 28:e78218.University of MichiganOur summarydoi:10.2196/78218
  3. 3.Fitz N, Kushlev K, Jagannathan R, Lewis T, Paliwal D, Ariely D (2019). Batching smartphone notifications can improve well-being. Computers in Human Behavior 101:84–94.Duke University · Georgetown UniversityOur summarydoi:10.1016/j.chb.2019.07.016
  4. 4.Richards AS, Bessarabova E, Banas JA, Bernard DR (2022). Reducing Psychological Reactance to Health Promotion Messages: Comparing Preemptive and Postscript Mitigation Strategies. Health Communication 37(3):366–374.Affiliation not yet confirmedOur summarydoi:10.1080/10410236.2020.1839203
  5. 5.Guo C, Pleiss G, Sun Y, Weinberger KQ (2017). On Calibration of Modern Neural Networks. Proceedings of ICML 2017, PMLR 70:1321–1330.Cornell UniversityOur summaryarXiv:1706.04599
  6. 6.Yuan H, Hernandez AA (2023). User Cold Start Problem in Recommendation Systems: A Systematic Review. IEEE Access 11:136958–136977.Affiliation not yet confirmedOur summarydoi:10.1109/ACCESS.2023.3338705

Keep reading

All notes
  1. 01When is it better for an AI assistant to say nothing?Whenever speaking would cost more attention than it gives back: when the person can't take it in, the evidence is thin, or nothing needs to change. The 2018 framework for just-in-time support (Nahum-Shani et al.) counts giving nothing as a designed option, and declining uncertain cases makes a system's other answers more reliable (Geifman and El-Yaniv, 2017).Timing and receptivity
  2. 02Do reminder apps change what people do, or just how often they open the app?Often only the second. In a six-month University of Michigan trial with 287 adults with high blood pressure (Golbus et al., 2026), notifications made people use the app more but did not raise steps in the next hour or improve food choices the next day. Opening an app is engagement, not benefit.Engagement is not benefit
  3. 03If I delete my data from an app, is it deleted from backups too?Eventually, but usually not at the same moment. EU and UK law require erasure without undue delay, and the UK regulator, the ICO, says backups count but may be put 'beyond use' until they are overwritten; Google Cloud commits to deleting customer data within about six months, and some backups are locked so that no one can delete them early.Privacy and deletion

Tre-Up is built on this research.

Pursue, the AI inside Tre-Up, is designed to notice when your day starts to slip and offer one small next step. The iOS app is in development. Invitations go out in small groups; leave your email and we will contact you when yours is ready.

Your email is used only for your invitation and important product updates. It is never sold. Unsubscribe at any time. Privacy policy