Homewise

What I did

• Led the voice of customer research, 8 interviews synthesized into six findings, including the reframe from price to scope that set the product's direction.
• Owned Hearth, the design system, and built it as living code with a drift linter that caught drift before it shipped.
• Reviewed and merged the other two designers' pull requests, so every contribution extended Hearth instead of fragmenting it.
• Built the front end prototype in Claude Code, the full agent flow from scope to human approval, then handed the dev team the repo to integrate the real backend, with no Figma in between.

Problem

Hiring a contractor is a guessing game

It is one of the most stressful purchases a homeowner makes, and eight interviews showed why. Trust starts social: people ask a neighbor or a friend first, because they assume online ratings can be gamed. When word of mouth runs out, they fall back on marketplaces they trust even less. Then the grind begins. They repeat the same problem to contractor after contractor, book visit after visit, and wait on quotes that come back impossible to line up against each other. Three phrases surfaced in almost every interview.

Insight

The price anxiety is really scope anxiety

Every homeowner unsure about price was actually unsure about scope. When contractors propose different fixes for the same issue, their quotes describe different work, so there is nothing to compare. One homeowner was quoted $250 to $7,000 for the same siding repair, and the telling part is that he had already worked out the answer: hire someone to diagnose and define the scope, then send that one scope out for comparable bids. He had described Homewise before we built it. Fix the scope, and the price becomes legible.

Solution

An agent that scopes the job before it shops it

Homewise acts on the reframe: scope first, price second. It turns a plain language problem into a defined scope of work, sends that one scope to every vetted contractor, and brings the bids back on identical terms, pausing for your approval before anything moves.

Final Design

Define the scope, in plain language

You describe the problem in your own words. The agent turns it into a structured, editable scope of work, the most important artifact in the whole product.

Design System

Hearth, the warmth at the center of every home

Homewise runs on Hearth, its own design system. It reads like a calm, premium homeowner tool, closer to Notion or Linear than a SaaS dashboard, with a humanist warmth most AI brands skip.

The palette is read by role, not hue: sage for trust, ember for caution, sky for info, over a warm cream canvas and near black ink. Type is one typeface, Geist, on an editorial weight ladder capped at 52px, because larger sans starts to shout. Shadows are banned, so depth comes from a five tier surface ladder and hairlines instead. And it is living code, not a static spec: every new token ships behind a drift linter.

Collaboration

We skipped Figma and built the design in code

Working closely with the PM and the engineers, we made an unusual call: skip Figma entirely. The design lived in the codebase from day one, a real React prototype on top of the Hearth design system, instead of static mockups. When it was ready, we handed the dev team the repo itself, so they could spin up their own front end environment and wire in the real backend and APIs without redrawing a thing.

Reflection

Trust was the hard part, not the automation

Homewise reframed what I thought the hard part of an AI product was. It was never the automation. It was trust. People only let the agent run when they could see the scope it built, the contractors it verified, and knew the final yes was still theirs. Defining scope before price, and pausing for approval before hiring, were not features. They were how the product earned the right to act.

It was also my first time building a front end prototype entirely in Claude Code, and the handoff is what sold me. The dev team took the working build as their starting point and wired in the real backend, with no mockups to redraw. The design wasn't a picture of the product. It was the first version of it.