RAG development
RAG systems that answer
from your own documents.
We build RAG (retrieval-augmented generation) systems: an AI knowledge base over your own documents, records and policies, used by an internal AI assistant or a customer support chatbot. Every answer shows where it came from.
Company handbook
“How much notice does a cancellation need?”
Cancellations need 48 hours’ notice. Inside 48 hours, the deposit is kept unless the manager approves an exception.
Source: Handbook · Bookings and cancellations
Illustrative answer. Your documents define the detail.
More AI automation services
What a RAG system is for.
A language model on its own answers from general training data. RAG makes it search your approved material first and answer from that, so the answer is specific to your business and can be checked.
- Internal AI assistant for policies, procedures and product detail
- Customer support chatbot on your website or WhatsApp
- Search and summaries across contracts, manuals and tickets
- Answers with citations, and a hand-off when sources are missing
- Customer support
- Routine questions answered from your own help content; the rest goes to your team with the conversation attached.
- Internal knowledge
- New staff find the procedure, price or policy without asking the person who has always known.
- Sales
- Accurate answers about products, terms and availability while the conversation is still warm.
- Documents
- Contracts, manuals and reports searched and summarised, with the passage each point came from.
How we build a knowledge base.
Most of the quality comes from the sources and the testing, not from the model.
- Choose the sources that are approved, current and owned by someone.
- Prepare and index them, keeping permissions where people should see different things.
- Test answers against real questions your team and customers ask.
- Launch with a review loop: missing or wrong answers are flagged and fixed at the source.
Where a RAG system stops.
A knowledge base is only as current as the documents behind it, so we design for the gaps.
- No guessing
- When the sources do not answer the question, it says so and hands over.
- No mixed permissions
- People only get answers from material they are allowed to see.
- No stale answers
- Each source has an owner and a way to update it.
Common questions
What is RAG, in plain terms?
Retrieval-augmented generation. Before answering, the system searches your documents for the relevant passages and gives them to the language model, which writes the answer from them and cites them. It is how an AI assistant can answer about your business without being retrained.
Which documents and systems can it use?
Common sources are Google Drive, SharePoint and OneDrive, Notion, help-centre articles, PDFs, spreadsheets and database records. We check formats and access during discovery.
Is our data used to train AI models?
Data handling — which provider, where data is stored, and whether it may be used for training — is agreed in writing before implementation. By default we choose settings that keep your documents out of model training.
Can the same knowledge base serve customers and staff?
Yes. One indexed source can power an internal assistant and a public chatbot, with different permissions and different rules about what each may answer.
Bring a question your team answers every week.
And the document that should answer it. That is enough to see whether a knowledge base would help.
A 30-minute conversation. No technical brief needed.