One field per domain
Keep product lines, sites, or subjects in their own fields. A question about one never drags in the noise of another, so answers stay sharp as your library grows.
Paddock · Private Document Intelligence
Your knowledge,
Your knowledge,
ring-fenced and answerable
Paddock turns your manuals, policies, and internal knowledge into answers your team can trust, with the exact page cited every time. Run it against a cloud model, or keep it fully private on hardware you control.
What Paddock Does
Answers you can stand behind
A wrong answer from a document assistant is worse than no answer, because someone acts on it. Paddock is built for the questions where the number has to be right.
01
Every answer cites its page
Each answer links to the page it came from. Your engineer clicks through and reads the source in one step, instead of trusting a paragraph and hoping. Citations open the original document at the right place, figures included.
02
Table-precise, not table-adjacent
Ask for a torque value, a weight limit, a fault code, a part number. Paddock returns the exact figure from the table with its page, not a paraphrase that rounds it or reads the wrong row. This is where generic document search quietly fails, and where technical teams get burned.
03
Grounded, or it tells you
Paddock answers from your documents and cites them. When the answer is not in your material, it says so rather than inventing one. For a maintenance manual or a policy set, an honest "not found" is the safe answer, and the one your auditors want.
04
Diagrams answer too
Schematics, wiring diagrams, and charts are indexed alongside the text. A question about the forward power schematic returns the figure, as a thumbnail you can open, not a sentence describing where it might be.
Ring-Fenced by Design
A paddock is a ring fence around what matters
Yours can be a topic, a moment in time, or a single tenant. Draw the ring fence and every question stays inside it.
Ask as of a date
"What did the maintenance manual require on the day of the incident?" Paddock answers from the revision that was current then, not the one you hold today. Point-in-time recall for aviation effectivity, insurance claims, and legal discovery, where the date is the whole question.
One deployment, strict walls
Serve many customers or business units from a single install, with hard separation between them. Each ring fence holds its own knowledge and no one else's, so nobody's query reaches another's documents.
A new ring fence does not mean a new system. Add a topic, a time window, or a tenant, and Paddock keeps the rest of your knowledge exactly where it was.
Your Choice of AI
Your documents stay yours. You pick where the AI runs
Paddock keeps your library, your indexes, and your citations on infrastructure you control. The model that reads them is your call.
Start on a cloud model, or keep the whole thing private. Same product, your decision.
Point it at a cloud model. If you already run a frontier model in the cloud, Paddock uses it to phrase the answers while your documents and indexes stay on your side. You get going fast and keep the search private.
Or run it fully private. When the data cannot leave, Paddock runs the model on hardware you control, air-gapped, with nothing going out. This is the shape we specialise in, and where most regulated teams land: a hangar, a branch, a ship, a bank.
Deploy it as a Mac appliance that runs everything on one machine, or as containers your team drops into its own stack as infrastructure as code. Either way, your library and your answers live behind your firewall.
| Your documents | Stay on infrastructure you control, always |
|---|---|
| The AI model | Your cloud endpoint, or fully private on your hardware |
| Private mode | air-gapped · 0 outbound |
| Deploy as | Mac appliance, or containers (infrastructure as code) |
| Runs on | Your Mac hardware, your cloud, or your servers |
Cloud gets you started. Private keeps the data in. We build for the second one, and we will tell you which your case needs.
Ingest
Feed it what you already have
Point Paddock at the documents you keep today. It reads them where they are, keeps web sources in sync, and gives every source its own settings.
| Source | What it handles |
|---|---|
| Manuals and reports, including dense technical tables | |
| Websites | Support portals and docs sites, crawled and re-synced on a schedule |
| HTML / Markdown / text | Knowledge bases and internal notes |
| CSV / JSON | Structured records and exports |
| You get back | |
|---|---|
| Exact value | The figure from the table, with its page |
| Grounded prose | An answer built from your passages, cited |
| Figure | The diagram itself, as a clickable thumbnail |
| Honest miss | "Not in these documents," when it isn't |
Beyond Answers
Turn your knowledge into decisions
Retrieval is where it starts. Paddock lets your people interrogate the whole corpus, weigh what different sources say, and surface the evidence behind a call, without a document ever leaving your control.
01
Ask across everything at once
Put one question to your entire ring-fenced library. Paddock gathers the relevant passages from every source that bears on it and lays out what they actually say, so an analyst starts from the evidence instead of hunting for it.
02
Evidence, not opinion
Every claim carries the citation it came from. A recommendation traces back to the exact page that justified it, so the people who sign off can see the ground it stands on.
03
The reasoning stays home
The analysis runs where your data lives. Your knowledge is never shipped to someone else's model to be reasoned over, unless you decide it should be. The intelligence comes to your data, not the other way round.
The institutional memory your organisation spent decades building finally goes to work for you, on your terms, inside your walls.
Data Sovereignty
One ring fence per person, when you need it
Regulations like GDPR do not ask you to try. They ask you to prove. Paddock gives every individual, team, or customer their own ring-fenced store, so personal data is isolated by construction rather than by policy.
Separated by construction
Each person's data sits in its own ring fence. A query inside one can never reach another, so there is no shared index quietly mixing records that should never meet.
Right to be forgotten, cleanly
Remove an individual's ring fence and their data is gone, with nothing left bleeding into a shared store. The erasure is complete because the separation was real to begin with.
Point at where it lives
Keep each store on the hardware, in the region, or under the tenant the rules require. Data residency stops being a promise and becomes an address you can show an auditor.
Privacy that is designed in reads very differently to a regulator than privacy that is bolted on.
Scale
Built to hold your whole organisation
Paddock grows by sharding. Your knowledge splits into independent shards, and a question only touches the ones that hold the answer, so recall stays fast and sharp whether the library is a thousand pages or ten million.
Shards, not sprawl
Split knowledge by topic, tenant, or time. Each shard is self-contained, so adding to one never slows the rest, and a query is routed only to the shards that matter.
Patented binary search
Our patented binary search finds the right passages using up to 60x less storage than a traditional RAG system. The same knowledge fits on a fraction of the hardware, so a corpus that used to demand a cluster runs on a box you already own.
Fast at any size
Retrieval time holds steady as the library grows. Paddock searches shards in parallel and skips the ones a question does not need, so the last document lands as quickly as the first.
Less storage, faster answers, and a footprint small enough to keep the whole thing behind your own firewall.
Architecture
Built over years, not bought off the shelf
Paddock is one engine, tuned end to end. The models, the search, and the index were built together over years of our own research. That is why the answers land where generic tools guess.
Our own embedding and rerankers
Merino is our family of embedding and reranker models, built and tuned for the documents enterprises actually keep: dense tables, technical manuals, contracts. Generic models were trained on the open web. Ours were shaped for this.
A search we designed
Our patented binary search is why Paddock stays fast and light as the library grows. How it works stays ours. What it gives you is exact answers on a fraction of the hardware.
Measured, not asserted
On our own benchmarks Paddock puts the right source in its top results more than 95% of the time, and says so plainly when the answer is not there. Every claim here traces to a number we can show you.
This is not a wrapper around someone else's API. It is years of research, our models, our search, and our index, tuned together. You will not assemble the same result from parts on the shelf.
Paddock
Put your organisation's memory to work
Bring us a manual set, a policy library, or a support site. We will stand up a ring-fenced, cited, on-prem answer engine on hardware you control.