Notifications as behavior design

Source: The Ridiculous Engineering Of Notifications, Enrico Tartarotti, 13:15, uploaded 2026-07-08.

A notification is the rare product surface that starts the interaction itself. It can arrive during an idle moment, supply a reason to act, and repeat that prompt until the action becomes routine.

Three layers

1. Message design: The product chooses a detail, an open question, a possible loss, and a delivery context that make the prompt hard to ignore.
2. Habit design: Repeated prompts move an action from an outside cue toward a routine that can continue without the cue.
3. AI mediation: The operating system can now rewrite, shorten, group, reorder, or suppress the message before the person sees it.

Specificity beats shallow personalization

Putting a name into generic copy does little. A specific detail gives the notification a concrete relation to the person’s life.

• Google Photos can rank past days by photo volume, location, and visual themes, then select an image and label that point to one recognisable event.
• Loom withholds the viewer’s name. The missing detail creates a question that the app can answer only after it opens.
• Hinge can reveal a name while withholding the rest. This changes the question from “who liked me?” to “what is this person like?”
• Duolingo frames the prompt as a loss: keep the streak, rather than gain another lesson.
• Delivery time works as context. A prompt sent near yesterday’s session uses a moment when the person has already shown that they can act.

This is a useful distinction: specificity resolves uncertainty, while a curiosity gap preserves selected uncertainty. Effective prompts often do both.

Notifications as the push channel

Most product use starts with pull: the person gets bored, remembers a need, or chooses to open an app. A notification lets the product choose the moment.

The video places notifications between instant messages and email. Messages suggest “act now.” Email provides a durable inbox for “deal with this later.” Many product notifications occupy a third window: act within the next hour, after one or more repeated cues.

Repetition matters more than one tap. The stated Duolingo model is that a seven-day streak makes a person 2.4 times more likely to return the next day. The prompt first produces the visit; the maintained streak later supplies its own pressure. This fits gamification that changes behavior and variable reward and habit loops in social apps.

The ethical result depends on the behavior and the business model. A prompt can support language practice, exercise, or contact with friends. The same habit can also raise retention, sell storage, or make cancellation feel like a loss. “Useful” and “commercial” can be true at the same time.

AI becomes an editor

Notification design used to assume a direct path from product to person. OS-level AI adds an editor between them.

• A summary can remove the exact detail that made the original message useful.
• A model can attach a false claim to a trusted app identity. The video uses Apple’s incorrect summary of a BBC notification as the main failure case.
• Reordering and suppression can change which sender gets attention, even when the original text remains accurate.
• Product teams may start to add machine-readable intent, urgency, and context for agents, much as llms.txt addresses machine readers on the web.
• The design target then shifts: the message must first convince an agent that it deserves to reach a person.

That shift creates a control problem. The sender knows why it wants attention. The operating system knows more about the person’s current context. Neither should quietly decide that product growth and user value are the same thing. This belongs near human-centered AI and explainability and marketing as context.

Caveats

The video reports large effects from notification timing and design, a dataset of more than 200 million notifications, and research on disabling notifications. It does not name or link the studies in its description. Treat the figures as leads, not verified evidence.

The argument also moves quickly from current AI summaries to future notification agents. Rewriting and grouping already exist; agent-specific notification metadata is the author’s forecast.

Further reading / references

• Hooked: How to Build Habit-Forming Products, named in the video as the habit-design model.
• Figma Design Agent, shown in the sponsored segment.
• Related: dopamine and product use, revolt against technology, perception, attention, and memory in interface design.