Smart Organization App
Designing the intelligence layer, not just the interface.
One click — Foldr reads the folder and reasons through every file.
Role
Design engineer, founder
Duration
8 weeks design (still ongoing)
Tools
Figma, Claude code, VS code, GitHub
TL;DR
File chaos costs freelancers real time and credibility. I built Foldr because I lived it, then validated the market was bigger. MVP before interviews: AI reasoning can't be evaluated in the abstract. Two rounds of testing later, bringing it to market.
Finding the signal
Before building, I went looking for signals. Forum threads, product reviews, and community sites told a consistent story: users weren't just frustrated, they were actively requesting automation. The market had already formed around the need.
The browser extension path was intentional. Cloud drives are where the problem lives, and an extension meant no installation friction and a real-world proving ground before committing to a native desktop build.
The shortest path to validation
The MVP user flow was built around one hypothesis: that AI could reason about a folder's contents and suggest an organization that felt right to the person who owned it. Getting that hypothesis in front of real users as quickly as possible shaped every scope decision.
Rationale
- The user decides which folder to organize.
- If no folder is selected, the flow waits and returns to that choice.
- With a folder selected, AI analysis runs and produces a suggestion.
The MVP had one job: find out fast whether AI-driven organization is worth anything. Every decision before the suggestion is overhead, so the entry is the smallest one that reaches it — pick a folder.
Legend
- Action
- Decision
- Screen
Product roadmap
The roadmap is a sequence of learning stages, each with a question it needs to answer before the next phase opens up.
Immediate:
Ship the MVP happy path and get AI organizational reasoning in front of real users.
Near-term:
Add history and rules — features surfaced directly by Round 2 testing, not assumed.
Long-term:
Expand to local file systems and address the security and privacy questions that come with it.
Design
Designing the environment
The drawer embeds directly into Google Drive without displacing any native interface. The goal was to meet users where the problem already lives and make Foldr feel like a natural part of the environment rather than an overlay on top of it.
Built for the canvas
The drawer fixed the canvas before design began — a bounded panel with its actions pinned to the bottom edge.
Users need a control's meaning only while choosing — so the row stays compact at rest and shows labels on hover.
Designing for AI legibility
Transparency wasn't polish here. It was the basis for trust.
Streaming the reasoning fills the silence and shows the interpretation before the recommendation lands. Automation you can follow is automation you can verify.
Designing from insight
This insight didn't come from a usability test. It emerged from running the system extensively across folders of all kinds. A pattern surfaced: AI suggestions consistently fell into two operations, moving files into existing folders, or creating new folders when no appropriate home existed. What started as a long flat list of actions became a tabbed interface organized around those two mental models. An insight only possible because the designer also built and operated the system.
Foldr
Current selected folder
Suggestion
One flat list. Moves and new folders arrive interleaved, so two different kinds of decision have to be sorted out of a single run.
Defining context for quality
Context decided suggestion quality. The selected folder alone was too little to reason from, and the whole drive cost more tokens than the answer was worth.
Pairing a holistic read of the drive with the selected folder's specifics improved both the suggestions and the cost of producing them.
With only the selected folder, the model could reorganize within it but never tell whether a file belonged in a folder that exists.
Drive
+216 more
Parent
Selected
Building it
HTML prototypes, supplemented by Figma
The prototype is working HTML, because that gives agentic coding tools far more accurate context to build from than a static mockup can, with Figma supplementing it for surgical changes.
Building the engineering muscle
Agentic tools ship code whether or not you understand it, so reading every diff and owning the repo was deliberate. Reading constraints directly narrows the gap between intent and what ships.