DrawEvolve

The premise

Most AI feedback on creative work is stateless. You show it a drawing, it tells you what's wrong, and next time you show it a drawing it has no idea it's ever met you. That's not coaching. That's a very confident stranger with opinions.

DrawEvolve is built on the opposite principle: the critique remembers. A second critique on the same piece references the first one and evaluates whether you actually acted on it. Progress is the thing being measured, not the individual drawing.

The product position is AI as mentor, not replacement — the app has an Artist Bill of Rights, and nothing in it generates art on your behalf.

The constraint

I was the entire team. Design, iOS, backend, infrastructure, and every decision in between. That shapes everything downstream: I couldn't afford architecture that required a team to maintain, and I couldn't afford a cost structure that could bankrupt me while I slept.

I also started this not knowing Swift. I learned it in about two weeks and started building.

What I built

A drawing engine, from scratch. Metal tile-based rendering, a wet-ink stroke system, brush suite, layers, selection tools, symmetry, full Apple Pencil support, and portrait/landscape handling.

The renderer went through a multi-phase architectural migration to tiles.

An iterative critique system. Four distinct AI voice presets, and "Eve," a conversational coaching layer that maintains rolling summaries of your conversation history so context survives across sessions without unbounded token growth. Critiques reference prior critiques. A My Evolution dashboard turns critique history into a visible progress record.

Infrastructure that assumes the worst. Every model call routes through a Cloudflare Worker proxy that verifies JWTs, enforces App Attest, applies tiered rate limits, and hard-caps daily spend. Supabase with row-level security behind it. Sign in with Apple and Google via authorization code flow with PKCE.

That work isn't glamorous and it's the reason the product exists. A solo developer shipping an LLM-backed app without a spend ceiling is one abusive script away from a five-figure bill. The ceiling went in before the app went out.

The tradeoff I made

I shipped the tile-based renderer before retrofitting wet-ink onto it, which means the stroke system is running on architecture it wasn't originally written for until I go back and finish that work. I took the visible progress over the clean sequence, deliberately, because a renderer nobody can use isn't verified.

That's a debt I named rather than hid, and it's scheduled.

How I worked

I ran parallel Claude Code agents across git worktrees for most of the build. Not as a novelty — as the only way one person covers that much surface area in six months. Each agent held a bounded scope on its own branch, and I did integration and review.

Learning to decompose work so that agents don't collide is a real skill, and it's most of why the timeline was possible at all.

Outcome

Shipped to TestFlight in May 2026. Three builds; the third passed Beta App Review and was approved for external testing. Running with a beta group of working artists, including a tattoo artist who's been the heaviest user of the critique system.