Zlata Salyukova builds AI systems and 3D web, and designs kitchens in Cape Girardeau, Missouri.
I am Zlata. I build software — a soil-mapping demo for farm fields, a ComfyUI editor with 183 GitHub stars, a parametric cabinet tool that keeps plan and elevation in sync — and I design kitchens. I work from Cape Girardeau, Missouri, remotely across the US, and I am open to AI roles and commissioned work.
WORK
Selected projects
-
Web Design
Sites and interfaces
-
Nebula — App design
A bookmark manager built around spatial memory instead of folders. Saved links stay findable because you remember where they were, not what you filed them under.
-
InnovAIte — Consultancy
Selling the plumbing, not the demo.
AI automation for small businesses in southeast Missouri. Published prices, self-hosted models, and a site that says what it costs.
Problem
Small businesses get sold a demo. A chatbot that works in the sales call, then meets a real customer with a real edge case and nobody owns it. The model is rented, the prompts live in someone else’s notes, and the invoice arrives monthly whether it works or not.
What I did
Built the practice around the unglamorous half. Self-hosted models instead of per-seat APIs, agent systems for the work that actually repeats, document and workflow automation for the paperwork nobody wants. Then hosting, security and maintenance — because a tool that dies quietly is worse than no tool.
What happened
The site is live with the prices on it, plus writing on the three automations trades businesses actually ask for: missed-call-to-text, quoting and estimating, and scheduling follow-up. One person who can answer for the whole stack.
- 1 person, end to end
- 3 core automations
- Self-hosted models
- Live pricing published
-
XR WebSpace — Spatial framework
A storefront you can stand inside.
A spatial web framework — with a working furniture showroom built on it. Four view modes over one data model.
Problem
Product pages flatten everything into a photo, a price and a cart, then ask the customer to imagine the piece in a room. 3D configurators exist, but they are a viewport bolted onto a page: one product, no sense of place.
What I did
Built the space as the interface. A scene graph of cards laid out in three dimensions, category nodes that pull forward when you click them, and a pluggable view system — universe, flat, XR and VR — all reading the same content model. Drag to orbit, scroll to zoom, click to descend.
What happened
The demo runs. Aurel & Oak: ten pieces across five categories with a live cart, navigable from an overhead universe view down to a single piece, and the same content re-renders as a flat 2D map when you would rather look at it that way.
- 4 view modes
- 3D scene graph
- 1 content model
- Live demo
-
madebyz.studio — This site
The universe you are standing in. A Three.js scene with a three-level card hierarchy, camera orbit, and content that lives on the cards themselves rather than in a panel.
-
-
Creative Tech
Tools and systems
-
CabinetShape — Parametric design
One model, many views.
A browser-first parametric kitchen design workbench. Runs on the device — no server, no account.
Problem
Kitchen design software is a drawing program. Move a cabinet in the plan and the elevation, the schedule and the 3D view are now wrong, because they were never the same thing. Someone retypes the correction three times and hopes.
What I did
Built it around one parametric document. Plan, 3D scene, properties and exports all derive from the same validated model, so a change lands everywhere at once. A fixed CAD shell keeps the ribbon, catalog, both views and save state on screen together.
What happened
Phase B2 runs: an immutable catalog of base, wall and tall families with typed construction and finish options, grid and wall snapping with a wall/face/offset constraint that survives a drag, undo per committed action, autosave with a previous-good copy, and validated JSON round-trips.
- 1 canonical model
- 2 synced views
- 0 accounts
- v2 design schema
-
HaloField — Live demo
One flat rate for a field that was never flat.
Satellite soil intelligence for row crops. A working demo — open it and drive the map.
Problem
Fields get one flat fertilizer rate because a field looks uniform from the road. It never is. In the demo field, nitrogen runs 36 to 57 lb/ac — same bag, every acre.
What I did
Built it as a nutrient map: soil samples in, hex grid out, five layers, a value per cell, quartile zone breaks, satellite and terrain underneath. MapLibre over live Esri tiles.
What happened
It runs. Three demo fields, 170–198 cells each; zones export as CSV or GeoJSON for a variable-rate spreader. Load your own samples — parsed in the browser, nothing leaves the machine.
- 3 demo fields
- 170–198 hex cells per field
- 5 nutrient layers
- ≤4 management zones
-
Comfy Canvas — ComfyUI node set
The edit loop was in the wrong app.
A layered image editor that runs inside ComfyUI. Built solo, with AI assistance. 183 stars on GitHub, MIT licensed.
Problem
ComfyUI generates fast and iterates slow. Repaint a hand and you export the image, open a paint app, re-import it, re-run. Every version you liked comes back flattened — the layer you actually wanted is gone.
What I did
Put the editor inside the tab. Two nodes, sessions bound to the node, a real layer stack, non-destructive per-layer masks, brush, bucket, marquee, blend modes, and a prompt dock that remembers what you typed. Output pushes back in as a new layer.
What happened
v1.0 went fully local — no Flask server, no second browser tab, no split workflow. It is in other people’s pipelines now, and they file issues about it.
- 183 GitHub stars
- 12 forks
- 2 ComfyUI nodes
- v1.0 fully local
-
Nova — Research, in progress
Testing what everyone else assumes.
A from-scratch research environment for small mixture-of-experts language models. Quiet for now — open source later.
Problem
Everyone building with AI uses the same handful of models and inherits their assumptions. The questions worth asking — how experts should route, whether backprop is the only learning rule worth using — sit behind compute nobody can afford.
What I did
Built a lab instead of a wrapper. One spike per idea, each proving itself before the next builds on it: custom routing, alternative learning rules, a dashboard measuring perplexity and routing behaviour on every run — trained locally, from scratch. I direct the research; my team of AI agents does much of the building.
What happened
Four spikes through to working models. Nothing released yet. It stays quiet until it is worth using rather than worth admiring, and then it goes open source.
- 4 research spikes
- 6 GB consumer VRAM
- 0 hosted APIs
- AI agent research team
-
OpenClaw — Creative tech
A self-hosted agent system running a team of specialised assistants — orchestration, scheduling, memory, and tool access, all on hardware I control.
-
-
Branding
Identity and print
-
Coloring Books — Branding
A print-ready illustrated series produced through a reproducible generation pipeline, so forty pages look like one coherent book.
-
Identity work — Branding
Marks, palettes and type systems for small businesses. Built to survive being printed on a van, a shirt, and a 16px favicon.
-
-
Kitchen & Bath
Residential design
-
Shaker Kitchen — Full remodel
Full white shaker kitchen: uppers and lowers, granite counters, tile backsplash, appliance integration. Designed, ordered, and delivered to install.
-
Cherry Island Kitchen — Full remodel
Cherry cabinetry with a large quartz peninsula and island seating. Layout driven by the traffic path between the garage entry and the dining room.
-
Photo Gallery — Scroll through
Finished kitchens and bath installs. Drag to scroll through the gallery.
-
ABOUT
What I do, and what I want
-
The path here
Shop floor to studio
-
Where it started — About
Cabinet shop co-owner at twenty. Then design and sales, online pickup, kitchen and appliance sales, now AI systems. People ask how those connect. They do not, exactly — the constant is that I keep getting handed a mess and asked to make it work. Tools changed. Job did not.
-
The long way round — About
2018 — co-founded A B Cabinets, a six-person shop: three designers, three assemblers. 2022 — Karter’s Cabinet Depot; 200+ project files from first measurement to install. 2024 — online pickup, then the Menards kitchen and appliance desk. 2025 — InnovAIte. Different tools every time. Same job.
-
-
How I work
How it actually goes
-
How I work — About
I build the smallest real version first and put it in front of you, then keep going. Most of it now gets built with a team of AI agents — I set the direction, check the work, and fix what they get wrong. If something is broken I tell you before you find it. If I say it works, I watched it work.
-
What I build with — About
TypeScript, React and Three.js on the front. Python and Node behind it. Local models when the data should not leave the building. Fusion 360, Blender and 2020 Design when it has to be physical. I pick what stays maintainable after I hand it over.
-
-
Right now
Current focus
-
On the bench — About
Three things at once: this site, a parametric cabinet design tool, and a small agent team that runs on my own hardware. The last one is the interesting one — mostly because nobody has a good answer for what happens when your tools start doing the work.
-
Open to — About
AI roles, and commissioned work — builds, fixes, or the awkward project nobody on the team wants to own. Email reaches me faster than the phone, and I am available by appointment most days. If the work is adjacent to any of this, ask. The worst answer is no.
-
CONTACT
Start a conversation
-
Email
The direct line
-
Say hello — Contact
zlata.salyukova@gmail.com · 573-450-2522 — tell me what you are trying to make and I will tell you honestly whether I am the right person for it. Open to AI roles and commissioned work; available by appointment.
-
-
Project brief
Tell me the shape
-
What good looks like — Contact
The best briefs describe the problem, not the solution. What is broken, who it affects, and what has already been tried.
-
How a project runs — Contact
A short call, a written scope with a fixed price, then weekly demos of something real. No surprise invoices, no long silence, no handover document nobody reads.
-
-
Elsewhere
Where else to find me
-
Find me — Contact
InnovAIte Solutions for consulting. Etsy for the coloring books. Email zlata.salyukova@gmail.com or call 573-450-2522 — the fastest route to an actual answer.
-
Contact
Email zlata.salyukova@gmail.com or call 573-450-2522.
Notes
Available
Taking on select projects. Small enough to move fast, experienced enough to know what breaks.
Cape Girardeau
Working remotely across the US. On site when the project needs a person in the room.