A figure seen from behind, the back of the head showing, sits before a wall calendar of wooden pegs and hanging cards, while a small robot holds a sheet of tracing paper against the calendar to show where one meeting card would move, and a small brass bell for calling the other attendees stands unrung, the whole scene drawn with wide empty margins on every side.

Dropbox.Tech

Evolving our calendar assistant Reclaim to be AI-native without starting over

Greg Unrein, Josh Jensen and Christopher Wildman · 29 September 2026

Takeaway

Dropbox's engineers sent every AI agent change in Reclaim, their calendar assistant, through the same checks of scheduling rules that people's changes pass, and let users preview it first.

Summary

Reclaim is a calendar assistant, owned by Dropbox, that uses AI to find and move time for tasks, habits and meetings. Its users wanted to describe scheduling goals in their own words, but an AI model can read the same request in several ways, and some readings change other people's calendars. Writing on Dropbox's engineering blog, Greg Unrein, Josh Jensen and Christopher Wildman explain how they added an AI agent without building a separate path for it.

Key points

Every calendar change, whether a person, the automatic scheduler or the AI agent makes it, runs through the same validation and commit step. Engineers therefore change each operation in one place.
Preview Mode shows users a temporary version of their calendar with the agent's proposed changes. Users can check the effect on shared events before other attendees are notified.
To keep previews fast, the team rewrote the scheduler so that it calculates a proposed schedule without saving anything to the real calendar.
The team built its own agent software instead of using a general framework, which it found lagged behind the AI model providers' latest features. The cost is more code to maintain.

Implication

A product team that adds an AI agent can send the agent's actions through the same rules as people's, and show users the full effect before anything is applied. This is Dropbox's account of its own product, it gives no figures on use or errors, and applying it elsewhere is an inference and is not the authors' claim.

Suggested actions

Engineering

Send every change that an AI agent makes through the same validation and saving code that people's changes use, so that the product's rules are kept in one place.

Design

Before an AI agent's proposed change is applied, show users a preview of its full effect, including on other people, and apply it only when they confirm.

Derived by Working Surface from the article. Source line: Whether a request comes from a user, the automated scheduler, or an agent, the same Schedule Action type is used, including the same validation and commit process.

Source issue

30 September 2026: when building gets cheap, teams spend the effort on checks, tests and choosing a direction.