Thomas Tran

Founding Designer building MongoDB’s Agent Platform

without leaving your agent.

Built for AI-native designers. Skip the Figma round trip – turn a plan into live prototypes, gather team feedback on one board, and converge on the best direction.

01 – The problem

The hard part isn’t generating prototypes.

Designers already prototype in Cursor or Claude — then the work bounces through Chrome, Figma, and Slack: screenshot, paste, annotate, chase feedback, re-prompt. Context frays with every round trip.

02

Burst it into real prototypes

One /burst turns a designer’s plan into multiple live prototypes on a shareable board – so the team can review and decide.

03

A board the whole team reads

Designers and stakeholders pin comments to any frame. /burst revise synthesizes the feedback, sharpens the set, and converges on a direction — without another Figma detour.

Pinned comments on a Burst review board
Burst context setup — decisions and changes captured automatically

04

Context travels with the work

The agent already knows the designer’s brief. Burst carries that context, plus decisions and the why behind each direction, so the team isn’t guessing from screenshots alone.

Next steps

Continue testing Burst with other AI-native designers – tightening the review loop from plan to prototypes to decision.

runburst.ai ↗

An app I built and launched to help managers prepare 1:1 conversations, grow their people, and build lasting habits. Designed and shipped in 8 weekends.

florish.me ↗

Florish landing page

01

A co-pilot for managers’ 1:1s

Florish helps you prepare conversations, capture what matters, and follow through — so coaching and recognition become a habit, not an afterthought.

02

Feedback & coaching captured automatically

Florish surfaces feedback and recognition moments from your 1:1 notes, and helps you say the hard things well.

Florish feedback and coaching captured from 1:1 notes

03

Frame difficult conversations

Not sure how to say it? Florish helps phrase a sensitive message clearly and respectfully, using AI.

Help me say it — input and suggestion modals
Early AI-generated build — Mentra
Intermediate dashboard iteration

04 – HOW I BUILT IT

From rough build to a real design system

I iterated through ChatGPT, Lovable, Figma and Cursor — from a first AI-generated build to refined components and tokens.

Refining the flows and visual design in Figma

Figma file — flows and visual design

Set up colors, tokens, and reusable components in Figma

Design system — tokens, typography, components

05

Next steps

This was meant as an experiment for me to design, build and ship a product end-to-end. While I have no plans to market it, I still want to further improve it for personal use and learning purposes.

Changing the way we rent, buy and sell homes — centralizing the agent’s entire transaction into one place: Deals.

Compass Deals — deal detail on web and iOS

01 – The problems

Their workflow lived on paper

Before Deals, agents tracked listings across folders, notebooks and a wall-sized whiteboard — nothing connected, everything manual.

Handwritten listing board
Paper deal folders
Compass Deals dashboard on web and iOS

02 – The solution · Deals

One home for every transaction

Centralize all information related to a deal, and create magical moments where the tedious parts get automated — on iOS, web and desktop.

03 – Create a deal

From listing to active in a few taps

A guided flow turns a new listing into a live deal — pick a type, add the details, and it’s ready to work.

Create a deal flow across four iOS screens

04 –On the go

The whole deal in your pocket

Comps, listings and insights for every deal — the same source of truth, now on iOS for agents in the field.

Compass deal detail across three iOS screens

Building the platform from the ground up with a team of 20 engineers and 2 PMs

Work in progress — not yet publicly available.