Document processing
Invoices, delivery notes, statements and filings read, checked and filed. Unclear ones go to a person.
Find out more: Document processing
AI that does the work, and shows its working
We build AI into the systems you already run. Each piece takes on a specific job, shows its sources, asks a person when it isn’t sure, and runs where you decide. You get a fixed price up front and a cost report every month.
Jobs we hand to AI
Start with a job, not a technology. These are the ones we build most often.
Inbox and enquiries
Email sorted, routed and answered in draft. Your team presses send.
Find out more: Inbox and enquiries
Assistants for your data
Ask in plain English, get an answer with a link to its source. Read-only by design.
Find out more: Assistants for your data
Agents and automation
Admin moved between systems, with approval wherever money or customers are involved.
Find out more: Agents and automation
Research and monitoring
Registers, filings and websites read at scale, with every finding linked to its source.
Find out more: Research and monitoring
Computer vision
Cameras that check picking, read labels and handle product images. Pilots and demos, honestly labelled.
Find out more: Computer vision
Forecasting and prediction
Demand, risk and price models tested on your own history.
Find out more: Forecasting and prediction
You choose where the AI runs
Tier 1
A hosted model, through a UK or EU endpoint
The best quality for the least effort. Before any of your data goes to a provider, we check that its business terms rule out training on it, and we tell you which region does the processing.
Tier 2
Inside your own cloud account
The model runs in your AWS or Azure account, under your access controls and your logs.
Tier 3
A private model on hardware in the UK
Open-weight models on your hardware or ours. Nothing goes to an outside AI provider. Our own research and document reading run this way.
Storage location and processing location aren’t the same thing. We’ll tell you both, in writing.
How we keep it accurate
Tested on your examples
Before a pilot starts, we agree a set of your real examples and a pass mark. The AI has to meet it before it goes live.
A source behind every answer
Answers link to the record, page or screen they came from, so anyone can check.
A person approves what matters
Payments, messages to customers, changes to records: someone on your team signs them off.
Logged, budgeted, switchable off
We keep a record of what the system did, every workflow has a monthly budget with a hard stop, and there’s an off switch. For the most sensitive data we can switch off detailed logging, and we tell you where we have.
Start small, with a fixed price
You don’t need to commit to a big project to find out whether AI helps.
-
AI audit
Two weeks, fixed price. We find the three jobs most worth handing over, and the ones that aren’t.
£1,500 -
Pilot
Up to six weeks on one job, with the test set and pass mark agreed up front.
From £6,000 -
Build
We make it part of your systems, with approvals, logs and budgets. Fixed price.
-
Run
Monitoring, model updates and a monthly cost report. You can leave at any time and take everything with you.
Already using AI?
Code and security reviews
AI reads the whole codebase; a second, independent pass checks every finding.
Find out more: Code and security reviews
AI agent governance
A review of how your coding agents and automations are set up, plus a standards kit for your team.
Find out more: AI agent governance
AI we’ve built and run
Live
Warehouse analytics assistant
Answers plain-English questions about a 3PL’s warehouse. It can only call tested read tools, so every number matches a screen and links to it.
Live
Our own private AI platform
AI workflows on open-weight models on our own hardware, each with a budget, logs and an off switch.
We’ll tell you when AI isn’t the answer
Sometimes a rule, a report or a £40 subscription does the job better. The audit exists to find that out before you spend real money.
Related pages
Questions
What’s the difference between automation and AI?
Automation follows fixed rules: if this, then that. AI handles the messy part, such as reading a document, understanding an email or answering a question. Most good systems use both, and we use the simplest one that works.
Which AI models do you use?
We choose per job and write the choice down. Hosted models from the major providers, through UK or EU endpoints where available. Models inside your own cloud account. Or open-weight models on UK hardware. You’ll see the model, its version and where it runs.
Can you work with the AI tools we already pay for?
Often, yes. We can connect Microsoft Copilot, ChatGPT or Claude to your systems with read-only connectors, so the tool you already have can answer from your data.
Do you build chatbots?
Only when a chatbot is the right answer. A good knowledge base, or replies drafted for your team, often works better. If we build one for EU-facing customers, it tells people it’s AI, as the EU AI Act requires.
What about the EU AI Act and UK GDPR?
We design for both from the start: data-protection impact assessments, human review of decisions that affect people, and clear records of what the AI does. See how we use AI responsibly.
Get in touch
Tell us the job you’d hand over first.
One paragraph is enough. We’ll reply with honest thoughts on whether we can help, and what it would cost.