Self-hosted regulatory intelligence
Regulatory answers you can actually cite.
A compliance research assistant that runs entirely inside your own infrastructure. Ask it a question, get an answer grounded in the source text — without sending a single customer record to anyone else.
Illustrative example
Running in your VPC
Yes. Account disclosures must be delivered before the account is opened or a service is provided, whichever comes first. The specific items your disclosure has to cover — rate, compounding, fees and balance requirements — are enumerated in the sections cited below.
12 CFR § 1030.4(a)
12 CFR § 1030.4(b)
Reg DD staff commentary
3 sources retrieved from your corpus — nothing left the network
What it does
Everything it tells you, it can show you.
Four things a compliance team actually needs from a research tool, and no claims we can’t point at.
01
Answers with citations
Every response points to the specific section it came from. When the corpus doesn’t support an answer, it says so instead of inventing one.
02
Your data stays put
Deploy on-prem or inside your own VPC. Queries, documents and customer records never leave your network — there is no vendor API in the path.
03
A corpus you can audit
The regulatory knowledge base is inspectable and extendable. Put your own policies and internal memos alongside the public material.
04
Fits the stack you have
A standard API and an MCP server, so the tools and agents you already run can query the same knowledge base without a rewrite.
How it works
Three steps, and the order is the point.
01
Regulatory material is structured and indexed deliberately, not scraped. This is the part that takes the work, and it is the part that decides how good the answers are.
02
A question pulls the specific sections that bear on it, ranked and traceable straight back to source text.
03
A small open model, running on a single GPU on your own hardware, writes the answer from those passages and attaches the citations.
We are deliberate about that order. The value sits in the corpus and the retrieval, not in the model weights. That is why it runs on hardware you already own, and why it gets better as your corpus grows rather than when somebody else ships a new model.
Deployment
Runs where your data already lives.
Most compliance teams cannot send customer records to a third-party API, and most AI tools require exactly that. JDM is built the other way around: the corpus, the retrieval layer and the model all sit inside your perimeter.
There is no call out to a vendor in the answer path. That is a deployment decision, not a setting you have to trust us to leave switched on.
Deployment
On-prem or your own VPC
Hardware
Single GPU
Base model
Open weights, self-hosted
Integration
REST API and MCP server
Corpus
Yours to inspect and extend
Data egress
None
Lenders and payments
Origination, servicing and settlement rules
RIAs and wealth
Advisory conduct and reporting obligations
In-house counsel
Anyone answering to an examiner
Where we are
Early, and we would rather say so.
JDM Inc is pre-launch. The retrieval layer and the regulatory corpus work today. Answer quality is the thing we are refining now, with a small number of design partners who know exactly what they signed up for.
Regulatory corpus and retrieval
Working
Self-hosted deployment
Working
API and MCP integration
Working
General availability
Not yet
If you want to be one of the early teams, we will tell you plainly whether it is ready for your use case before you commit anything to it.
Design partners
Tell us what you would point it at.
Send us the question your team keeps having to answer by hand. We will tell you whether the corpus covers it today, and what it would take if it does not.
info@myjdminc.com
We reply to everyone.