AI, engineered for production
We build AI products, integrate AI into existing systems, and know the engineering it takes to make them trustworthy — grounded answers, fail-soft design, controlled costs.
What we do in AI
Build
AI products end-to-end: RAG answer engines with cited sources, semantic search, and AI content pipelines — from feasibility to live operation.
Integrate
Add AI to the systems you already run — LLM-powered features, semantic search over your own content, automation pipelines. No rewrite required.
Advise
Honest guidance on where AI fits your product, what it will cost to run, and where a simpler solution beats a model. Strategy grounded in systems we have shipped.
Shipped, not slideware
We built Business111, a production answer engine for UK businesses: retrieval-augmented generation with cited sources, semantic vector search, and an owned AI content pipeline spanning transcription, narration, and automated video. Every pattern on this page runs in production there today.
See the case studyHow production RAG works
Retrieval-augmented generation means the model never answers from its own memory. Every answer is retrieved-then-generated: grounded in a curated index you control, cited so every claim is checkable, and current because the index updates continuously — not when a model retrains.
1
Understand the question
A language model rewrites the question into search terms and extracts anything structured — cached so repeats cost nothing.
2
Retrieve from a curated index
The query runs against a continuously updated, trust-scored index — fast, cheap, and deterministic.
3
Generate only from the sources
The model composes a concise answer using nothing but the retrieved documents. No sources, no answer — never a guess.
4
Cite everything, stream it live
Inline citations link every claim to its source while the answer streams token by token.
AI use cases we've shipped
Not a capability list — a production inventory. Each of these runs live today.
How we keep AI trustworthy
Grounded, never free-form
Where AI writes anything a user reads, it is constrained to supplied source text. Facts come from your data; the model arranges them.
Fail-soft by design
Every AI call has a non-AI fallback. A provider outage degrades quality — plainer copy, keyword search — but never breaks the product.
Cost under control
Caching, heuristic gates, per-user rate limits, and model tiering keep spend predictable and proportional to the value delivered.
AI questions, answered
What is retrieval-augmented generation (RAG)?
RAG is an architecture where an AI model answers only from documents retrieved from a curated index, rather than from its own memory. Every answer is grounded in real sources and cites them, which keeps responses accurate, current, and verifiable. We used RAG to build the Business111.com answer engine for UK businesses.
How do you stop AI hallucinating?
By never letting the model answer free-form. We constrain generation to retrieved, trust-scored documents, require inline citations, and return a safe default when the sources cannot support an answer. Grounding plus citations means every claim is traceable to a source a human can check.
Can you add AI to our existing product?
Yes — and without a rewrite. We typically start with one high-value integration: semantic search over your content, an assistant grounded in your documentation, or an enrichment pipeline for your data. AI components run alongside your existing stack behind clear interfaces, engineered fail-soft so your product keeps working even when the AI layer degrades. First integrations typically reach production in weeks, not quarters.
Which AI models and providers do you work with?
We work with OpenAI and Anthropic models for generation, OpenAI embeddings for semantic search, Whisper for speech-to-text, and Elasticsearch for lexical and vector (kNN) retrieval. We choose per use case and keep model choices configurable, so providers can be swapped as the market moves.
What does a typical AI project involve?
A short feasibility phase first: where AI genuinely helps, what data you have, and what it will cost to run. Then an incremental build — retrieval and grounding first, generation second, evaluation throughout — delivering working software at each stage rather than a demo at the end.
How do you keep AI running costs predictable?
Caching, so repeat questions never hit the model twice; heuristic gates that skip AI calls when a simpler check can decide; per-user rate limits; and model tiering — small models for routine steps, larger ones only where quality is user-visible.
What happens when the AI provider has an outage?
Nothing breaks. Every AI call in our systems has a non-AI fallback: search falls back to keyword results, generated copy falls back to neutral templates, captions fall back to timed text. Quality degrades gracefully; features never hard-fail.
Do we own the system you build?
Yes. Full ownership transfers to you: code, infrastructure, prompts, evaluation suites, and operational runbooks. No managed AI vendor sits between you and your features, and there is no lock-in to us either.