Frame
FRAME — Inside Frame · Architettura, Web & AI Engineering, Graphic Design

Available for projects
Studio — Castiglione del Lago (PG)

An independent studio working across architecture, web and graphic design — every project kept in frame.

space · simplicity · meaningful
ScrollIndex
Selected Work — DEV(10)

The software development side of the studio: websites, platforms and ai-oriented products we build, ship and keep running.

01PixedenmarketplaceNode · GraphQL · Mongo · RedisA design-assets subscription marketplace live for about a decade and rewritten end to end — separate Node services for auth, payments and downloads behind a Next.js BFF, self-hosted. Around 15k unique visitors a day.with Pixeden LLC02Orion Icon Librarysvg web appNext.js · Redux · MongoReal-time SVG icon customisation in the browser — recolour every named layer, adjust strokes, export SVG, sprite, icon-font or PDF. Same pipeline behind a bespoke enterprise icon-set generator built for McKinsey.with Pixeden LLC03Lingremlearning platformNext.js · Capacitor · GraphQLSpaced-repetition language learning, live on web and iOS from one codebase. A model writes the lesson content into validated structured formats; a separate GraphQL API owns the scheduling, the audio and the rate-gating, deterministically.with Pixeden LLC04The Collection Parismembers’ platformNext.js · Mongo · SwiftA members’ club platform for car collectors: a web CMS plus Capacitor iOS companion apps, and a native CoreNFC plugin that turns the member’s iPhone into a physical access badge.with Pixeden LLC05Mockupccinorender enginePython · FastAPI · Next.jsPhotoreal product mockups without Photoshop: a Python engine decodes the perspective and mesh warps out of a PSD smart object and composites artwork onto them near-interactively, behind FastAPI and a Next.js editor. Built by pairing with AI — the render engine stays deterministic by design.in progress06i-NEEAidentity + platformNext.js · GraphQL · MongoBrand identity first, then a multilingual site for a Swiss energy consultancy — a kind-parameterized headless CMS and a custom contact-to-admin request pipeline, built to grow as they add internal tools.07Dharma Pointsite + headless cmsNext.js 16 · PPR · Mongo AtlasWebsite and headless CMS for a Buddhist meditation centre in Pomaia — a block-based visual editor, an events calendar and a magazine the centre edits itself, with no developer in the loop.08Aperturemulti-tenant saasNext.js 16 · tRPC · DrizzlePhotographers run their own branded photo-selling store on a subdomain: Postgres with row-level security, organisations, and money routed straight to the photographer through Stripe Connect with a platform fee.in progress09Spikcapture appNext.js 16 · Capacitor · IndexedDBShoot a photo, record a voice note over it with a waveform overlay, tag the place. Everything stays on the device — IndexedDB, offline, no account — or leaves as an encrypted link that expires. Web, iOS and Android from a single codebase.studio product10Neocornerheadless wordpressNext.js · WPGraphQL · PHPA restaurant group edits in WordPress; the animated Next.js frontend renders untouched. We built both halves — the host-side theme and a custom React renderer that maps every Gutenberg block, over WPGraphQL, to its own component.

with Pixeden LLC — built at Pixeden LLC, where our lead engineer is CTO & full-stack engineer

Capabilities3 disciplines
01 / architettura

Space

  • residential & adaptive reuse
  • interiors & detailing
  • landscape & pavilions
  • permitting & site direction
02 / dev

Systems

03 / graphic

Signs

  • identity & brand systems
  • editorial & print
  • signage & wayfinding
  • art direction
Practice — AI engineering02 / dev

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.

01 / modes

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.

02 / boundary

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.

03 / grounding

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.

04 / evals

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.

05 / safety

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.

06 / cost

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.

Machine-readable

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.

What we refuseno model output ships unevaluatedno metric we can’t proveno chatbot without a jobno model we can’t swap out

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
© 2026 FrameBack to top ↑