Ship the AI product your competitors keep demoing.
Codelucent is an AI design studio in Kansas City and Tokyo. Napkin to App Store, prompt to production: mobile apps, LLM systems, payments, cloud. We run our own apps, so we know exactly what breaks at 2 a.m. and how to build so it doesn't.
Teams and products we have built with
Three ways in. One bar: it has to ship.
From Google Loon and a $100M+ exit to founding Particle Space and helping companies 3x.
David Biga has been writing software since he was ten. He started in C++ building games, paid for high school with PHP contracts off Craigslist, and spent his university years at Google Loon building the launch systems that let stratospheric balloons lift off autonomously from anywhere on earth.
He then joined EyeVerify in Kansas City as one of its early engineers, designing the C++ core of the identity-verification SDK that carried the company (later Zoloz) to a $100M+ acquisition by Alibaba’s Ant Financial. That exit lit the entrepreneurial fuse: David went on to found Particle Space, a real estate data platform that turned fragmented property records across the US and Japan into clean, AI-enriched APIs, and ran it from zero to revenue to an acquisition in 2023.
Along the way he has been a founding engineer, CTO, and CEO across a string of Kansas City startups, helping found companies that have since 3x’d, raising rounds, closing sales, and still shipping code. He hosts The Gitlit Podcast on the real journey of tech founders, and when he is not building he is mountain biking, hiking, or cave diving (yes, he is certified, which is how Scuber happened).
- Founder, Particle Space (US + Japan real estate data APIs), acquired 2023
- Early core engineer at EyeVerify / Zoloz, acquired by Alibaba for $100M+
- Google Loon: autonomous balloon launch systems, front and back end
- Founding engineer, CTO, and CEO roles across Kansas City startups that 3x’d
- Host of The Gitlit Podcast; builder of Pivotly (#8 AI product on Product Hunt)
- Ships his own apps: Tori, Akiya Listings, Scuber, Paystack, Leasey
- Age 10First lines of C++
Chicago. Games in Blender, then PHP contracts through high school.
- UniversityGoogle Loon
Front and back end launch systems for autonomous stratospheric balloon launches.
- Kansas CityEyeVerify → Zoloz
C++ core of the identity-verification SDK. Acquired by Alibaba (Ant Financial) for $100M+.
- FounderParticle Space
Real estate data platform, US and Japan. Zero to revenue to acquisition in 2023.
- OperatorCTO / CEO roles
Helped found and scale Kansas City startups that have since 3x’d. Fundraising, sales, and code.
- NowCodelucent
AI design studio and advisory in Kansas City and Tokyo. Ships its own apps, treats yours the same way.
We eat our own cooking.
Seven products we design, ship, and run ourselves. Marketplaces, fintech rails, proptech, health, and vertical SaaS, live on iOS, Android, and the web.
Akiya Listings
Find and buy abandoned homes in Japan.
Scuber
Lost it in the water? Get it back.
iOS and Android apps launching soon
Paystack
Payment rails built for agents and marketplaces.
Thrive AI Health
Your all-in-one AI health coach.
Numbers, not adjectives.
The whole AI stack. No handoffs, no hand-waving.
From the first prompt to the production runbook. Pick one capability, or let us compose the whole product.
A production RAG pipeline.
Click a stage to see the code behind it.
Connect to your docs, tickets, warehouse, and databases. Versioned ingestion pipelines re-embed only what changed.
// Versioned ingestion with source-version tracking
export async function ingest(source: Source) {
const docs = await source.fetchSinceLastRun()
for (const doc of docs) {
const chunks = chunk(doc, {
strategy: source.strategy, // semantic | fixed | layout
size: source.chunkSize,
})
await embed(chunks, {
model: "voyage-3",
cache: true,
version: source.embeddingVersion,
})
}
}Already have AI in production? Let's find out if it's lying to you.
We audit retrieval quality, faithfulness, safety, cost, latency, and drift on your real traffic, fix the worst offenders, and wire evals into CI so the fixes stick.
Explore evaluationsTwo studios. One standard. Your time zone covered.
Four steps. Zero mystery.
Discovery
We map your users, data, workflows, and constraints, and agree on what "good" looks like in measurable terms.
Design & architecture
Flows and interface, retrieval shape, model routing, infra, guardrails, and the eval plan that proves it.
Build & evaluate
Weekly demos. Every iteration gated by evals on your data, not vibes or vendor demos.
Ship & harden
Store launch or production deploy in your cloud, observability and cost controls wired, runbooks handed off.
“We were able to scale our tech operations with a fraction of the cost and time it would have taken to build in-house.”
Got an AI idea? Bring it. We'll tell you the truth about it.
30 minutes with a founder: what to build, what to skip, and what it should cost. No pitch deck, no account manager.