Artificial Intelligence now
What we do in AI
Language models that run inside your own network
For organisations that cannot send data to an outside AI service. We install, tune and run the model on your servers or on a national cloud.
Learn more
Software agents that prepare the work, with a person approving
An agent carries out several steps across your systems and stops for approval where a decision matters.
Learn moreAI that completes, checks and summarises your documents
A document arrives half-finished. The model fills the gaps from your own records, checks it against the rules, flags what does not match and writes a short summary for the reviewer.
Learn more
Assistants that answer customers and staff, day and night
Chat assistants for web, mobile and social channels. They answer common questions, read the tone of a message and pass hard cases to the right person.
Learn moreForecasting, routing and early warning from your own data
Models that predict demand, plan routes and flag problems before they grow.
Learn more
The right model, sized and tuned for your work
Bigger is not always better. We compare open and commercial models on your own tasks, then tune and shrink the one that fits your hardware and your budget.
Learn moreKeep the model running, current and affordable
A private model is not finished at launch. We monitor it, update it, control its cost and report on it.
Learn more
Find out what AI can do for you, and what it cannot
A short, fixed-scope review. We look at your data, systems and rules, and tell you which use cases are worth building, in what order, and at what cost.
Learn moreAnswers from your own files, with the source shown
Retrieval-augmented generation (RAG) lets a model answer from your documents instead of from memory. Staff see the answer and the page it came from.
Learn moreForms, scans and files turned into structured records
We read documents at volume, check them against rules and route them to the right person.
Learn more
Bots that explore your data and report what they find
A data bot works through large data sets on its own. It finds patterns, writes up what changed and keeps learning as new data arrives.
Learn moreOffers and recommendations built from behaviour
Models that learn what each user does and suggest the next offer, product or activity.
Learn more
Systems that read images, video and speech
Computer vision and speech recognition for places where information is not typed. Bangla speech and traffic camera systems are in build.
Learn moreKnow how good the system is before your users do
We build a test set from your real cases and score the system against it. Before launch, and after every change.
Learn more
Rules, limits and records for AI agents
An agent that can act needs limits. We set what it may touch, where it must stop for a person, and how every action is recorded.
Learn moreWhat we built, and what it did
Language models running inside government networks
AI that reviews documents for a mobile financial service
A dispatch engine that assigns orders with machine learning
A sales and distribution app with AI route planning and data bots

A platform that predicts customer service needs
Web, mobile and social conversations in one AI-assisted console

Four stages. Stop after any of them.
Find out if it is worth building
A short, fixed-scope review of your data, systems and rules.
- Interviews with the people who do the work
- Review of data and systems
- A ranked list of use cases with effort and cost
- A written recommendation
See it working on your own data
A working system for one use case, built on your real data.
- One agreed use case
- A working system, not slides
- An accuracy or performance report
- A costed plan for production
Go live in your environment
The full build: integration, security testing, training and go-live.
- Integration with your systems
- Security testing before launch
- Training and handover documents
- Go-live support
Keep it running and keep it safe
Monitoring, patches, model updates and reports for as long as the system runs.
- Monitoring and alerting
- Patches and updates
- Model and data updates
- Regular reports for audit
Certified and recognised
Information security and quality management, applied to every build.
Three regional and national awards for technology work.
A-CSM, PMP, CISSP, AWS, Azure and ITIL. Microsoft, AWS and Google Cloud.
Who we have worked with



















What clients ask first
Does our data leave our network?
No. The model runs on your servers, a private cloud or a national cloud. We agree the location in writing before work starts.
Which models do you use?
Open models and commercial ones. We pick per workload and explain the choice, the hardware and the running cost in writing.
How do you know the answers are right?
We test the system on your own cases before launch. You get the accuracy report. Unclear cases go to a person.
Who makes the final decision?
A person. The system prepares the work and shows its source. People approve anything that affects rights or money.
What do we need to start?
One use case, access to sample data and one person who knows the work. The first stage tells you if it is worth building.
