AI workspace · Case study

Designing and shipping an AI workspace for better proposals.

Project Paperplane (a working name, the product is in private preview) is an AI workspace for freelancers and studios who live or die by proposals: drafting, client pipeline, approvals, pitch decks, and the analytics to learn what actually wins work.

Product
Paperplane (working name)
Role
Designer and builder · solo
Status
Working product, private preview
Team
One person, several AI tools
Stack
React · TypeScript · Cloudflare
Scope
Product design to deployment
01

The difficult part

Proposals are where independent designers spend their most anxious hours for their least certain returns. The raw material already exists: past proposals, past pricing, what won and what sank. But it lives in fifteen documents across three tools, so every new proposal starts from a blank page anyway.

The design problem: make AI drafting feel like reusing your own judgement, not generating generic filler. The moment an AI proposal reads like an AI proposal, it costs you the job.

PROPOSAL, DRAFTED WITH AIAI suggests scope + pricingfrom past winning proposalsSend →PIPELINE · APPROVALSDraftReviewSentWonWHAT ACTUALLY CONVERTS
Fig. 01One workspace: draft with your own past wins, track the pipeline, learn what converts.
02

The product story

The workspace centres on the proposal editor, where AI suggests scope, structure, and pricing drawn from your own history rather than from the internet's average proposal. Around it: a lightweight CRM for the client pipeline, an approvals step for teams, pitch-deck generation for the meetings that follow good proposals, and shared document links so you know when a client actually opened the thing.

Analytics closes the loop. Win rates by proposal type, where clients stop reading, which sections correlate with a yes. The pitch is simple: stop guessing what converts.

03

Design system and interaction thinking

This one is also an implementation story. I designed the product, then built it: React, TypeScript, and a Cloudflare deployment, with AI tooling in the loop from first wireframe to production. The design system stayed deliberately small, a working set of documented tokens and patterns, because a solo product punishes every component you cannot maintain.

Building it myself changed the design. Interaction details that would have died in a handoff document, like optimistic saves and inline AI suggestions that never steal focus from typing, survived because the designer and the developer were the same stubborn person.

04

Result

A working product, live in private preview: proposal generation, CRM, analytics, approvals, and document sharing, shipped end to end by one designer. It is also my standing answer to a question I hear in interviews: “can you work with engineers?” I can be one for a while, which turns out to be the fastest way to respect them.

NoteThe product is getting its public name and launch separately, so this case study uses a working name and schematic figures for now. Happy to walk through the live build on a call.
05

What changed in my thinking

Shipping solo recalibrated my sense of what is expensive. Visual polish is cheap. State management, edge cases, and empty states are expensive. Since Paperplane, I design the expensive parts first, and my Figma files have carried a lot fewer decorative frames.

Next case studyRiskabilitie