AI EngineeringRAG & AI search
RAG & AI search
Answers traced to source. Retrieval-augmented generation connects a model to your own content, so every answer cites the document it came from, and says so when there is nothing to cite.
A model on its own answers from memory; a RAG system answers from your documents and shows its working.
For contracts, policies, technical manuals and case files, the citation is the product: an answer you cannot verify is an answer you cannot use.
What we build.
OpenKit builds retrieval systems that answer from your own documents and cite the passage every answer came from.
- Search across your documents
- Contracts, manuals, tickets, case files, drives.
- Cited answers
- Every response linked to the exact source passage.
- Hybrid retrieval
- Semantic and keyword, tuned to how your documents actually read.
- Access-aware answers
- The system respects who is allowed to see what.
- Runs inside your controlled environment
- Where policy or contract requires it: see Private AI.
Every system ships with the evaluation set it was measured on, so accuracy stays a number your team can re-run rather than a claim from us.
Retrieval is one of four builds under AI engineering, alongside agents, language-model development and voice.
Where a raw model lets you down.
Four reasons a general model cannot answer a question about your business, and the reason retrieval exists at all.
- It makes things up
- A language model will produce a confident, plausible answer with no basis in fact, a real risk when a wrong answer drives a business decision.
- Its knowledge is frozen
- Trained to a cut-off date, it cannot reliably speak to recent events, current regulations, or this quarter’s numbers.
- It has no proprietary context
- It knows nothing of your policies, your customers, or your internal history, so its answers stay generic and impersonal.
- Retraining is expensive
- Keeping a model current by retraining is slow and costly. A retrieval system updates by changing the documents, not the model.
The same question, grounded.
“What is our notice period for a break clause?”
Raw model
“A break clause typically requires six months’ written notice.” It reads fluently, it may well be wrong about your lease, and the model gives you no source to check it against, so the error surfaces only when someone acts on it.
Retrieval system
“The notice period is nine months, per clause 14.2 of the lease dated 3 March 2023.” Retrieved from your document, cited to the exact clause, and (where the wording is ambiguous or missing) it says so rather than filling the gap.
Your search live in four weeks.
- Week 1
Identify
Document audit and question workshop
- Accuracy baseline measured
- Week 2
Build
Your documents indexed and searchable
- Retrieval tuned to how they read
- Week 3
Prove
Benchmarked against your baseline
- Cited answers checked by your team
- Week 4
Scale
Rollout and training
- Next document set scoped
Beyond fetch and answer.
Where a single retrieval pass is not enough, we reach for one of three patterns, and each one answers a different kind of question.
- Agentic RAG
- Retrieval as a reasoning loop: an agent decomposes a complex question, decides which sources to query for each part (a document base, then a live API, then a database) and synthesises one grounded, multi-step answer. The right pattern when a single retrieval pass cannot cover the question.
- GraphRAG
- Retrieval over a knowledge graph as well as text, so the system understands the relationships between records rather than only their wording. That answers connected questions (which project used the same supplier as the one a named person led) that plain text search handles poorly.
- Multi-modal RAG
- Retrieval that reaches beyond text into images, diagrams and audio, so a model can consult a technical drawing or a recorded call to answer a question.
Where a retrieval build sits.
- Inside an AI Audit and Transformation
-
Your documents and the questions are mapped, then the first retrieval system ships in the same four weeks.
How the audit runs - As a Bespoke Build or with an Embedded AI Lead
-
More document sets, more teams, tighter tuning: commissioned as one piece of work, or carried as a running queue inside your team.
How the embedded engagement runs
The honest range for UK retrieval work.
Published UK market ranges for taking a retrieval system from scope to a working deployment. The single biggest driver of the figure is not the model: it is how clean and well-structured your documents are, because most of the work is preparing them. OpenKit scopes each build to an outcome and never publishes its own rate card.
- Retrieval or knowledge system
- £15k-£50k
- One clean source and a single channel at the low end; multiple sources and complex retrieval at the high end.
- Multi-source / agentic retrieval
- £40k-£150k
- Several systems and reasoning steps coordinated behind one answer.
- Regulated environment
- +10-20%
- Security documentation, access controls, audit trails, evidence.
Source: OpenKit AI development cost guide, published UK market ranges.
When grounding is not the answer.
Four cases where retrieval is the wrong tool, and we say so before anyone spends.
- There is nothing to ground in. With no body of documents, retrieval adds nothing: a plain model or a custom LLM fits better.
- The task is a lookup or a calculation. A database query is cheaper, faster, and more reliable than wrapping a language model around it.
- The source data is contradictory or stale. Retrieval will faithfully return the wrong thing; fixing the data has to come first, and we will tell you before building.
- Nobody will keep the knowledge base current. A retrieval system is only as good as its documents: without an owner, its answers decay as the content ages.
If the answer is a tuned model rather than retrieval, that is large language model development, and we will point you there instead.
“… The transparency is fantastic; you can instantly verify every AI output against source documents, which builds trust with our users.”
Lease review with verifiable citations against the original PDF is the BAiSICS build; the other two run the same pattern over commercial leases and clinical triage. All case studies
What teams ask before the first document audit.
What is retrieval-augmented generation (RAG)?
Retrieval-augmented generation connects a language model to your own documents. Instead of answering from what it memorised in training, the model first retrieves the relevant passages from your knowledge base and then answers from them, with a citation. OpenKit builds custom RAG systems so the answer is grounded in your data and you can check where it came from.
How is this different from a chatbot on our website?
A website chatbot follows a script or answers from general training. A retrieval system reads your own documents and cites the passage each answer came from, so your team can check it.
Why use RAG instead of a raw LLM like ChatGPT?
A raw model invents plausible-sounding facts, has a fixed knowledge cut-off, and knows nothing about your internal information. Retrieval changes each of those: answers come from sources you can open, the knowledge is as current as your documents, and it is your data the model reads. For anything where a wrong answer has a cost, grounding is what makes the system usable.
Our documents are a mess.
Normal, and part of the build: BAiSICS runs on large, complex, poor-quality documents. The document audit in week one tells us what we’re working with.
Can it hallucinate?
A RAG system is constrained to your sources and cites them; where no source exists, the honest behaviour is “not found”, and that’s how we build.
Does that remove the risk entirely?
No, and it would be dishonest to say so. A well-built system retrieves the right passages, answers only from them, cites each claim, and refuses when it cannot find support, so wrong answers become rare and, more importantly, checkable. We design the refusal and citation behaviour deliberately rather than hoping the model behaves.
Does our data train someone else’s model?
No. Your content stays yours, and we contract with model providers on terms that keep it out of their training data. Where that is not enough for your obligations, the whole system runs privately inside your own environment.
How do you keep our data secure in a RAG system?
The knowledge base and the model run where you choose (a UK region or your own servers) with role-based access so a user only retrieves what they are permitted to see. OpenKit is ISO 27001, ISO 9001 and Cyber Essentials certified, and the systems we build are designed to operate under UK GDPR. Client data is used only to deliver the engagement: it is not retained afterwards and never used to train external models. Every answer carries an audit trail of the sources it used.
How accurate is it?
We measure it: week three benchmarks the system against your own baseline, on your own questions, before anything rolls out.
How do you measure retrieval accuracy?
Against your own material. We build an evaluation set from real questions and expert-approved answers, then measure retrieval quality and answer accuracy against it before launch. For EMQN’s assessment platform we tested six models across 150 scenarios in six languages, and reported the honest gap between per-criterion accuracy and strict whole-report accuracy so the human-in-the-loop decision was evidence-based.
Can a RAG system work with our existing documents and systems?
Yes. OpenKit integrates retrieval with the document stores, wikis, ticketing systems, and databases you already run, through their APIs. The retrieval layer indexes your content where it lives; we handle the messy part (inconsistent formats, scanned PDFs, mixed languages) so the system reads what your team actually has, not an idealised version of it.
Who offers RAG solutions for enterprises in the UK?
OpenKit builds bespoke RAG systems around your own data and hands them over: ISO 27001 and ISO 9001 certified, deployed in a UK region or on your own servers, with no per-seat licence that scales against you. A UK team does the work, and what you have at the end is the system itself rather than an account on ours.
What does a RAG system cost in the UK?
Published UK market ranges put a retrieval or knowledge system at roughly £15,000 to £50,000, and multi-source or agentic retrieval spanning several systems at £40,000 to £150,000 (OpenKit AI development cost guide). Regulated environments add ten to twenty percent for the security and audit work. What moves the figure most is the state of your documents rather than the model you pick, which is why the document audit comes first.
Do we own the RAG system, or is it locked to a vendor?
You own it. OpenKit builds on open components and hands you the index, the pipeline, and the deployment, running on infrastructure you control. It keeps working whether or not you engage us again, and you are free to change it or hand it to another supplier. The point of the engagement is a capability your team can run and extend without us.
Not ready to talk? The free AI readiness check scores where you stand in about five minutes.
Find your first workflow.
We start with a conversation, audit where AI actually pays back, and build the first automation into how your team already works.
We reply within one working day.