AI engineers inside your team until the system is live
A team of senior AI/ML engineers in London, formerly at Rolls-Royce. We take the work your people do by hand, from calls and photos to documents and systems, and turn it into a product in your environment.
Inbound call
“Water damage in the kitchen, it happened last night.”
2 photos received
Claim form
- Policy number
- 48213
- Excess
- £250
Claim opened
Assessor booked for Thursday. Written to your claims system.
Prototypes are cheap now. Products are not.
Most AI initiatives stall between the demo and the deployment. Closing that gap takes engineers who know products.
The last mile is engineering
A prototype handles the happy path. A product handles bad audio, blurry photos, messy scans, permissions, and the day it breaks at four on a Friday. That is what we do.
We know what good looks like
We have shipped products of our own. We start from the problem and the person doing the job, cut what is not needed, and build what gets used, not just what runs.
Nothing to sell but the work
No platform, no vendor's product to push. We build on whatever suits you, and you own the code. Our measure is the number agreed up front: hours back, cost per case, error rate.
What we take on
We start with the work your team does by hand every week, then build everything that replaces it: the models, the data platforms, and the product around them, front end to back end.
- Voice agents that handle calls
- Intake, bookings, follow-ups and checks, with outcomes written to your systems and a person to hand over to.
- Agents that read documents
- Contracts, statements, scanned forms and reports: extract, classify, check and route, with a person reviewing the exceptions.
- Computer vision for photos and video
- Damage photos, site footage, inspections and product images, described, measured and flagged where your team already works.
- Agents that run a workflow end to end
- Cases, claims and applications across several systems, from intake and evidence to a drafted decision and an audit trail.
- Machine-learning models on your data
- Forecasting, scoring, classification and anomaly detection, trained on your history and monitored so they stay honest.
- Data pipelines and big-data platforms
- Ingest, clean and join your data at scale, on the cloud you already use: the groundwork every model and agent needs.
How it works
From first call to a system your team relies on.
- 01
A 20-minute scoping call
You describe the problem. We say honestly whether it is a fit and roughly what it would take.
- 02
A free prototype
If it is a fit, we build a quick working prototype of your problem, free: on a few of your documents, redacted if you prefer, or on realistic samples we make to match yours.
- 03
A two-week pilot
Two weeks on your real data at a fixed price, with the numbers we will be judged on agreed up front: hours saved, cost per case, error rate. Then you decide on the full build.
- 04
The engagement
Pilot, build and go-live, inside your team. Phase by phase below.
A typical engagement, phase by phase
Usually 12 to 16 weeks
Phase 1
Pilot
Two weeks on your real data: map the process with the people who do it, prove the approach, then fix scope and price for the build.
Phase 2
Build
A working system in your environment from week one, reviewed by your team against real cases every week.
Phase 3
Live
Monitoring on, your team trained, exceptions routed to a person, and the agreed numbers reported every week. Then a clean handover, or we stay on for support.
A few things we hold to
- We sit with your team, not in a slide deck.
- Working software from the first weeks, not a report at the end.
- Your data stays in your environment.
- Evaluation and monitoring are part of the build.
- No platform. You own the code and can leave at any time.
Is this for you?
We would rather say so on the first call than disappoint you in week eight.
A good fit
- A named problem: a process your team does by hand every week.
- Finance, legal, pharma and life sciences, industrial operations or another data-heavy business, from growing firms to teams inside large organisations.
- You want to see it working in weeks, not read a strategy in months.
What we need from you
- The owner of the P&L in the room: one person who can make decisions without a committee.
- Access to the people who do the work, and to the data, in your environment.
- An hour a week to review real output and tell us what is wrong.
- A view on who runs the system after go-live: your team, or us on support.
Who we are
We met building AI and machine-learning systems at Rolls-Royce, then went on to found products of our own. Between us, years of forward-deployed engineering inside pharma, financial services and industrial clients, shipping AI that survives contact with real data, real users and real compliance teams. Full backgrounds on the first call.
Mohammad Tanweer
Lead AI architect
Ships multi-agent and RAG systems into production for a Google Cloud Premier Partner's clients. Has sat on the client side of vendor pitches, so he knows what a demo hides.
Junru Xiong
AI and product
Built document AI at Rolls-Royce, then led the agentic OS that a financial services team runs in production, helping take it to its first £1M ARR. Founded Starmoon, IncarnaMind and Retapp.
- More than eight years each inside large organisations: aerospace, pharmaceuticals, financial services, industrial operations and telecom.
- Founders as well as engineers, so we know what it takes to get a product used, not just built.
- Computer vision, NLP, big-data platforms and MLOps by background, and full-stack engineers with it: web and mobile front ends, back ends and data, so one team ships the whole product.
The people you meet on the first call are the people who build the system.
Work we have done
Described without naming the client or employer. We walk through each one, screens and code, on the first call.
0 week
from a qualifying call to a free working prototype of your problem
0%
cut in prototype-to-production time for an enterprise delivery team
0s
of scanned documents and handwritten reports read by our document AI, saving hours and days of manual data entry for a global pharma client
0+ yrs
average experience building ML and AI systems inside large organisations
Inside organisations
- Document AI for aerospace, energy and pharma
- Computer vision and NLP reading thousands of scanned documents and handwritten field reports, pulling out tables and key values at over 90% accuracy. For a global pharma client, it saved hours and days of manual data entry.
- Deal ingestion and investment memos at a property investment platform
- An in-house AI module reading deals at over 98% accuracy, cutting days of work down to minutes and helping land the first paid customer. Its services are now being rebuilt as agent tools.
- Clinical-trial data platform for a London biotech
- Built on Google Cloud and published by Google as a customer case study, with drug-discovery pipelines on AlphaFold2 running alongside it.
- Agents for a Google Cloud Premier Partner's clients
- Multi-agent workflows with persistent memory and retrieval, including an analytics agent that gives a retailer's business teams natural-language access to their BI. Evaluation harnesses cut prototype-to-production time by about 30%.
- Risk and compliance models on Google Cloud
- Risk-insight classification models hardened and deployed on Google Cloud, so risk and compliance teams can use them in day-to-day operations.
Products we have founded
- Starmoon AI
- A voice agent in hardware: a conversational device small enough to sit inside a toy, speech in and out on a tiny board, plus a companion app. Open source, and used for comfort, such as helping a child through nerves before a medical appointment.
- IncarnaMind
- An open-source research assistant that answers questions across a whole library of PDFs and text files, with the source open beside the chat, saved sessions, and hosted or local models. Teams run it in production.
- Retapp
- Intake and pricing for electronics refurbishers. Devices are catalogued from web and mobile apps, graded, priced against live and sold listings in the UK, France, the US and Germany, then approved for sale or exported in bulk.
550+ GitHub stars
800+ GitHub stars
4 markets priced liveQuestions we get asked
- Agents that take calls, read photos and video, and work through documents and systems. Underneath, models trained on your data, computer vision and pipelines at scale. And the product around it: web and mobile front ends, back ends and data, not only the model. All built with evaluation, monitoring, permissions and a clean hand-off to a person.
- Inside your team, with your data and systems, rather than in an office building a demo. Software firms call this forward-deployed engineering. It is our whole business.
- Hosted models, or open-weight models on your own infrastructure, on the cloud you already use. No platform to steer you towards, and you own the code.
- The prototype is free. After that, a two-week pilot at a fixed price, then a fixed price for the build, agreed once we have seen the real data. No hourly invoices.
- It ships with evaluation and monitoring, and your team is trained to run it. Take it over entirely, or keep us on for support.
- Any size. What matters is a process done by hand, an owner who can decide, and data we can access.
Tell us about the work your team does by hand.
Twenty minutes. We will say honestly whether it is a fit.