Services / AI
AI that holds up in production.
Custom models, agents, retrieval and memory, built by the team that ships them and measured against the work they replace.
[ 01 ]Our approach
Most AI projects stall between the demo and the first real customer. The model is rarely the reason. What is missing is the engineering around it: evaluation sets that say whether it works, retrieval that finds the right evidence, guardrails that keep an agent inside its job, and a clear line between what the model suggests and what the code decides. That is the work we do, from custom model training to agents that run unattended.
[ 02 ]What we build
12 AI services, one accountable team.
Each one has its own page: what it is, what we build, where it pays off, the stack and the questions buyers ask.
- 01
Custom AI Model Development
A model trained on your data, owned by you.Models trained or adapted for one job in your business: classification, extraction, ranking, forecasting or generation, with the data pipeline, evaluation and serving to run them. - 02
LLM Fine-Tuning and Distillation
Frontier quality at a fraction of the cost.Fine-tuning and distilling open language models so they follow your format, tone and policies, run faster and cost less per request than a general model. - 03
AI Agent Development
Agents that finish the job, inside the rules.Agents that plan, call tools and complete multi-step work in your systems, with the model's suggestions separated from the decisions code makes. - 04
AI Workflow Automation
Hours of back-office work, done in minutes.End-to-end automation of document-heavy, rules-heavy processes, where AI reads and drafts and your systems of record stay the source of truth. - 05
RAG Development
Answers from your documents, with citations.Retrieval-augmented generation over your documents and data: hybrid search, reranking and answers that cite the passage they came from, or say they cannot answer. - 06
AI Memory and Knowledge Graphs
AI that remembers what your organisation learned.Persistent memory and knowledge graphs for agents and teams: facts, decisions and commitments extracted from your work and kept with their sources. - 07
MCP Server Development
Your product, usable by every AI assistant.Model Context Protocol servers that expose your product's data and actions to Claude, ChatGPT, Cursor and other agents, with authentication and least-privilege tools. - 08
Voice AI Agents
Every call answered, qualified and logged.Phone and in-app voice agents that answer, qualify, book and hand over to people, with turn-taking fast enough to feel like a conversation. - 09
Document AI and Intelligent Document Processing
Paperwork turned into clean, checked data.Extraction from invoices, contracts, forms, IDs and scans into validated structured data, with confidence scores and review where it matters. - 10
Private LLM Deployment
AI on your infrastructure, data never leaves.Open models deployed in your cloud, on-premises or air-gapped, with inference tuned for cost and latency and the security controls your auditors expect. - 11
LLMOps, Evaluation and Guardrails
Know your AI works before customers find out.Evaluation suites, observability, guardrails and red-teaming for AI already in production or about to be, so quality, safety and cost are measured on every change. - 12
Predictive ML and Forecasting
Decisions made on what will happen next.Forecasting, anomaly detection, churn, fraud and pricing models on your structured data, deployed into the systems where decisions are made.
[ 03 ]How we deliver
Four steps, one team, start to finish.
The same people scope it, build it and stay after launch. Timings are typical for a first release; we agree yours after the deep dive.
- 01Week 1
Find the decision
We pick the decision or task worth automating, measure how it is done today and agree what better means in numbers.
- 02Week 1 to 2
Build the eval first
A labelled test set from your own data comes before any prompt or training run, so every change is scored, not argued.
- 03Weeks 2 to 10
Build with guardrails
Models suggest, code decides. Permissions, injection checks, human override and audit logs are part of the first version.
- 04Ongoing
Ship and improve
We launch to real users, watch cost, latency and quality per request, and feed failures back into the eval set.
[ 04 ]Related work
Things we have already shipped.
- Machine learning platformGaiaTrain anything. Deploy anywhere.
- Data platformSynthesize.ioProduction-ready synthetic data, generated in seconds.
- Continual learningDAGILearning that doesn't forget.
- Legal technologyHolmesThe legal AI that remembers everything your firm has done.
- AI infrastructureZynd AIThe network where AI agents work together.
- Decision enginesClearLoadRoutes every task to a human or an AI.
- Data pipelinesJerseyHarvestUnstructured sources in, clean datasets out.
- Developer toolsOverseeXBreaking changes, delivered as tested pull requests.
- Knowledge systemsDeltaMemoryInstitutional memory for implementation teams.
- Venture intelligenceAlphaScoutUnbacked startups, matched to your thesis.
- Defense systemsProject NemesisA defense algorithm grown from a fly's brain.
[ 05 ]Resources
Problems we found, and our proposals.
- AI agents3 min read
Why AI agent pilots stall before production
ProblemAgent pilots impress in demos and stall before production because nobody can show they work, limit what they can do, see what they did, or overrule them.ProposalDraw a hard decision boundary: the model scores and drafts, deterministic code decides and acts, every step is logged with its reasoning, and a person can overturn any decision in one click.Read the proposal - AI security3 min read
Prompt injection is an architecture problem
ProblemAny agent that reads untrusted content and can act can be steered by instructions hidden in that content, and no prompt or filter reliably separates data from commands.ProposalAssume injection will happen and limit what it can achieve: keep untrusted content away from privileged decisions, give tools least privilege, put consequential actions behind code-level checks, and break the path to exfiltration.Read the proposal - AI security3 min read
MCP servers are your new supply chain
ProblemAgents trust tool descriptions and outputs from MCP servers they install like packages, so a poisoned description, a compromised server or an over-privileged token can steer or rob them.ProposalPut an MCP gateway between agents and servers: pinned and reviewed tool manifests, per-user scoped tokens, sandboxed local servers, output sanitising, egress allowlists and a full audit log.Read the proposal
One company at a time