Skip to content
Talk to us

Consulting

Service

Help running AI on your own terms.

We help teams put AI where their data already lives: on devices, in the browser and on their own servers. We measure before we build, and we hand over everything we make.

Talk to us

Four things we know well, because we ship them.

On-device and private AI

Choose, quantize and run models on phones, laptops and your own servers, with GPU and NPU acceleration and offline-first apps.

Built on what we learned shipping Orb

Document AI, Arabic included

OCR and extraction for documents in Arabic, English and mixed scripts, evaluated on your own pages before anything goes to production.

Built on our work on Razin OCR

Agents and the web

MCP servers, WebMCP, and turning the web apps you already run into tools agents can call safely.

Built on what we learned building Deputy

Evaluation before investment

Reproducible benchmarks on your data, so model, vendor and hardware choices rest on numbers.

Built on our evaluation harness

How an engagement runs.

  1. 01

    Scope

    One call and a written problem statement we both agree on.

  2. 02

    Baseline

    Measure the options you already have on your own data.

  3. 03

    Build

    Ship the smallest thing that moves the number.

  4. 04

    Hand over

    Code in your repository, documentation, and reports you can rerun.

What you keep

  • Code in your repository, under your control.
  • Measurement reports you can rerun yourself.
  • Documentation written for the people who'll maintain it.
  • No lock-in to us or to a single model vendor.

Tell us what you're trying to do.

A short description is enough to start. We'll reply with whether we can help and how we'd measure success.