Private knowledge assistant

An internal assistant that answers from your documents, on your own servers

Your organisation already holds the answers, spread across contracts, reports, manuals and wikis that nobody has time to read. A private assistant makes that material answerable in plain language, cites where every answer came from, and never sends a document outside your network.
  • Answers cite their sources
  • Runs air-gapped if required
  • You own the model and the index

Illustrative sample. File names and answers are fictional.

Research assistant · internal
Offline
Summarise the dosing changes in the 2024 protocol amendments
Two amendments changed dosing. Amendment 3 lowered the starting dose for patients over 65 from 20 mg to 10 mg. Amendment 5 added a two-week titration step before the maintenance dose.protocol-amendment-03.pdfprotocol-amendment-05.pdf

Answered in 5.8s on local hardware

Try another question

  • On your servers
  • No external APIs
  • Data stays in

Why build it privately

The documents worth asking about are the ones you can't upload

The material that would benefit most from an assistant is usually the material under the strictest handling rules: contracts, patient records, unreleased research, engineering drawings, pricing. That is exactly what a hosted assistant is the wrong home for.

This is the same argument as sovereign AI generally, applied to one workload. If your constraint is regulatory rather than contractual, the rules on where data may be processed differ by country; see data residency by region.

  • Handling rules

    Contracts and regulations often say where a document may be processed and who may see it. Uploading it to a third party can breach both.
  • Permissions already exist

    Your file shares already know who may read what. An assistant that ignores those rules is a data leak with a friendly interface.
  • Answers need provenance

    In regulated work, an answer without a source is not usable. Anyone reviewing it has to be able to open the document it came from.
  • Cost that stops scaling

    Per-seat pricing grows with headcount, not with value. Your own hardware costs the same whether ten people or a thousand use it.
TopicHosted assistant on your filesPrivate assistant on your infrastructure
Where documents sitUploaded to the provider's storageNever leave your file shares and network
PermissionsUsually per workspace, not per documentRetrieval filtered by your existing access rules
ProvenanceVaries by product; often noneEvery answer cites the passage it came from
Model changesThe provider upgrades on their scheduleYou pin a model version and test before changing it
AuditLimited to what the provider exposesEvery question, source and answer logged on your systems

What we build

The parts a working assistant actually needs

A demo is a model and a vector store. A system people trust enough to use daily needs the six pieces below, and most of the engineering time goes into the ones that are not the model.

  • Ingestion for your real formats

    Connectors for the file shares and systems you already run, handling PDFs, Office files, exports and scanned documents. Scans go through OCR first; rotated and low-quality material is its own engineering problem.
  • Retrieval that finds the right passage

    Chunking tuned to how your documents are structured, embeddings generated on your own GPUs, and hybrid keyword-plus-vector search with reranking, because pure vector search misses exact terms like clause numbers and part codes.
  • Generation with citations

    An open-weight model, quantized to fit your hardware, that answers from the retrieved passages and cites each one. Prompting and output filters define what it does when nothing relevant was found.
  • Access control at retrieval time

    Permissions applied when passages are fetched, not requested in a prompt. Users get answers built only from documents they are already entitled to open.
  • An evaluation set from real questions

    A graded set of questions your team actually asks, so changes to chunking, the model or the prompt can be measured rather than argued about. This is what makes the system improvable after launch.
  • Audit logs and monitoring

    Every question, the sources retrieved and the answer returned, logged on your systems. Retrieval quality is monitored so you can see when new document types stop being found.

How we build it

Retrieval quality first, model choice second

Most assistants that disappoint do so because the right passage never reached the model, not because the model was too small. We spend the early weeks on retrieval and measurement, which is also where the cheapest gains are.

A useful rule when budgeting: improving what gets retrieved is almost always cheaper than moving to a larger model, and it does not increase your hardware bill.

  1. Stage 1

    Start from the questions, not the documents

    We collect the questions your team actually asks and grade what a good answer looks like. That set becomes the evaluation harness, and it decides which document sources are worth ingesting first.
    Graded question set
  2. Stage 2

    Ingest and chunk for your structure

    Contracts, manuals and reports each break into passages differently. We tune chunk size and overlap against the evaluation set rather than accepting a default, and add OCR where documents are scanned.
    Clean passages with source metadata
  3. Stage 3

    Index on your own GPUs

    An embedding model runs on your hardware and writes into a vector database inside your environment. Nothing is sent out for embedding, which is a step teams often miss when they audit a pipeline.
    Private vector indexVector databaseLangChain
  4. Stage 4

    Hybrid search and reranking

    Keyword search catches exact identifiers; vector search catches paraphrase. A reranking pass puts the strongest passages first, which raises answer quality more than a bigger model usually does.
    Ranked, relevant passages
  5. Stage 5

    Size and serve the model

    We pick an open-weight model that fits your GPUs at your target latency, quantize it, and benchmark it on your own questions. The model is chosen against your hardware, not the other way round.
    Served model with measured latencyOpen-weight LLMQuantization
  6. Stage 6

    Measure, then harden

    We run the evaluation set against the finished pipeline, agree the behaviour when nothing relevant is found, wire in access control and audit logging, then hand over the code and artifacts.
    A system your team can run and improve

What it takes to run

Hardware sized to the task, not to a headline number

Model size is a sizing decision driven by your GPUs, your users and your latency target. A well-retrieved passage in front of a mid-sized model beats a large model guessing from memory, and it costs considerably less to run.

  • Quantization cuts memory use so a larger model fits the GPUs you have
  • Concurrent users and target response time drive sizing as much as model size does
  • Embedding and generation can run on separate hardware when that is cheaper
  • We size it with you during the assessment, before you buy anything

For a worked example of the trade-off, our guide on on-premises versus cloud deployment covers how the same decisions play out for vision workloads.

Where it can run

  • Air-gapped on-premises

    Model, index and logs on servers inside your facility, with no internet connection at any stage.
  • Your own cloud account

    Deployed into your AWS, GCP or Azure tenancy and region, with private endpoints your cloud team controls.
  • Managed by us, hosted by you

    The same isolated environment, with monitoring and retraining handled by our managed services team.
Compare deployment options

We have built this

An air-gapped assistant over proprietary medical research

For Atacana we built PharmaBrain, a retrieval assistant over thousands of proprietary medical reports that runs entirely offline on local servers. It uses Mixtral 8x7B, a 46.7B-parameter mixture-of-experts model, quantized to 8-bit so it fits local GPUs, and answers in five to seven seconds with no data leaving the client's environment.

Getting started

From your first questions to a system your team runs

  1. Step 1: Assessment

    Scope and feasibility

    We review your document sources, access rules and the questions you want answered, then design ingestion, retrieval and serving for your environment.

    • NDA on request
    • Hardware sized before you buy
  2. Step 2: Proof of concept

    4–6 weeks

    We build the pipeline on a real subset of your documents and benchmark it against an evaluation set drawn from your own questions.

    • Measured on your data
    • Runs on your hardware
  3. Step 3: Production

    Harden, deploy, hand over

    Access control, audit logging and monitoring go in, then we deploy into your environment and hand over the code, models and runbooks.

    • You own the IP
    • Raw data stays with you

FAQ

Questions teams ask before they start

  • Where the documents go. A hosted assistant sends your files and every question to a third party, and you are bound by their retention terms, their model changes and their availability. A private assistant keeps the documents, the index, the model and the logs inside your own network. The trade is that you provide the hardware and we build the pipeline, rather than paying per seat forever.

Book a strategy session

Scope a private knowledge assistant

Tell us which documents you want answerable, where they live and any rules on where they may be processed. An engineer will reply within one business day, under NDA if you need it.

  • Send the form, it takes 2 minutes
  • We reply within 1 business day, under NDA if you need it
  • A 30-minute call to scope feasibility and next steps

Tell us about your project

By submitting, you agree to our Privacy Policy. We never share your details.