AI • RAG • B2B SaaS • UK

A grounded AI knowledge platform — not another hallucinating chatbot.

A UK professional-services firm was drowning in internal enquiries that had already been answered somewhere in 40,000+ documents. Generic chatbots hallucinated. Off-the-shelf AI search couldn't be trusted with client data. We built a Retrieval-Augmented Generation platform on Azure UK-south where every answer is traceable to its source document.

Client(name withheld — reference available)
IndustryProfessional services (B2B)
ServiceAI Software Development
Timeline11 weeks MVP → production
Team2 ML engineers + 1 full-stack + 1 designer

📋 To publish: replace the anonymised client with a named firm, add a screenshot of the citation UI, and ideally a short recorded demo showing a grounded answer with source links.

The problem

Expertise locked in documents nobody could find.

40,000+ client files, policy documents, briefing notes and prior-work outputs across SharePoint, network drives and email. Seniors spent an hour a day answering questions that had been answered before. Consumer AI tools would either refuse (safety) or hallucinate (unsafe). Neither was defensible.

The approach

Grounding > generation.

Every answer the platform gives must cite the source document and paragraph. The model can refuse. We don't let it generate from its own training. Two-week discovery defined the evaluation harness — a gold set of 200 real questions from the client, scored on accuracy, relevance and safety before a line of production code was written.

What we built

A four-layer RAG architecture.

Outcomes

After 60 days of production traffic.

95%+
Gold-set accuracy (grounded answers)
63%
Internal support queries deflected
11 wk
MVP to production
0
Data left UK regions

Client quote

"The citation UI is what sold it internally. Every answer shows its working. We're comfortable putting it in front of partner-level staff because we can see exactly where each claim comes from."
Head of Knowledge ManagementUK professional-services firm (reference available on request)

📋 To publish: replace with named client quote + role + headshot once permission confirmed.

Tech stack

What we used.

Azure OpenAI (UK-south)Azure AI SearchNext.jsPythonFastAPILangChainpgvectorPostgreSQLEntra ID / SSOOpenTelemetry

Related

Services behind this project.

Got an AI use case that needs to be defensible?

Free 30-minute call. We'll tell you honestly whether it's RAG, fine-tuning, or "not yet ready for production".

Book an AI discovery call