An independent studio working across architecture, web and graphic design — every project kept in frame.
The software development side of the studio: websites, platforms and ai-oriented products we build, ship and keep running.
with Pixeden LLC — built at Pixeden LLC, where our lead engineer is CTO & full-stack engineer
Space
- residential & adaptive reuse
- interiors & detailing
- landscape & pavilions
- permitting & site direction
Systems
- websites, web apps & saas
- ai & agent engineering ↓
- interaction & motion · webgl
- headless cms & tooling
Signs
- identity & brand systems
- editorial & print
- signage & wayfinding
- art direction
AI is a material, not a feature. The engineering around the model is the product.
We design the loop, not the prompt: a probabilistic core inside deterministic scaffolding, so the parts that touch your data, your users and your money behave the same way every time. That discipline is what makes AI safe to put in front of your customers. Nothing ships without evaluation.
Orchestrate & pair
Agents for repeatable, high-volume work — we design the loop, hand it tools over MCP and structured outputs, and review what comes back. Pairing for the novel, design-heavy parts, hands on the wheel.
Deterministic scaffolding
A probabilistic core wrapped in validation, retries, structured outputs and fallbacks. The model fills a validated format and hands it back; the scheduling, the writes and the money stay deterministic on the far side.
Retrieval with a floor
Answers grounded in real data, with a relevance threshold underneath them. Below the floor nothing comes back at all — it says it found nothing rather than padding the answer with something adjacent.
Tests that cost nothing
An eval you can’t afford to run is a comment, so ours run on every commit — committed vectors scored with plain cosine: no key, no tokens, no network, same result every time.
Blast radius, not filters
You can’t filter your way out of prompt injection. What you get to decide is what the model can do once someone succeeds — read-only tools, one typed door, none of your data within reach.
The cheapest token
The cheapest token is the one you never send: cache breakpoints on the static prefix, capped loops, embeddings computed offline and committed. Latency gets fixed the same way — by not doing the work twice.
In production, in both directions — in some projects the model is in the product: it writes into validated structured formats, while deterministic services keep the scheduling, the money and the rules. In others it never ships at all — it stays in the process, the pair we build with, around engines that have to behave identically on every run. Wiring up an LLM is the easy part; the value is knowing which of the two a problem is, how far to let the model reach, and where it has no business going.
Our knowledge base is also an MCP server — four read-only tools, no model behind it. Point your own AI client at it and it reads the work directly, instead of scraping a rendered page. The site publishes an llms.txt for the same reason.
We design the space, the system, and the surface. One studio, three disciplines, held together by a single frame.
- Based
- Loc. PinetaCastiglione del Lago (PG), IT
- Founded
- 2018independent
- Disciplines
- Architettura · DevGraphic
- Coordinates
- 43.3° N12.4° E