Commercial lending
Our own lending business. Borrower packages are read and cross-checked, and lenders are matched to each deal, with every figure tied to its page.
Auditable AI decisions · the guardrail for AI agents
SteadRail is the guardrail for AI work where one wrong number is costly. A model reads every page. Code checks every citation and holds the veto on hard rules. People make the final call, with the source page already open.
The problem
The Department of War has almost 1.7 million people on GenAI.mil, and they have built more than 100,000 agents.1 Wherever one wrong number is costly, from clearing a supplier’s foreign ownership to financing a defense manufacturer, those agents need guardrails. It’s the same problem across agencies that lend, license or buy, and in banks.
01
Filings, manuals, applications and scans, still read and cross-checked by hand.
02
The same company, owner or number written four ways across four documents.
03
Language models read well, but they can’t prove where a number came from. In one published test on company filings, a leading model with retrieval got 81% of questions wrong or declined to answer.2
04
Even when set to be consistent, a model’s accuracy can swing by up to 15% from one run to the next.3
How it works
A language model reads every page and returns each figure with its page and the exact words behind it.
Code checks the model’s work: the quoted words must be on that page, and the number must be inside them. Then fixed checks run across the documents.
Code holds the veto on hard rules. Anything ambiguous goes to a person with the source page open. Nothing gets guessed.
disclosure.pdf · page 14Every job goes to the model that fits it. Frontier or open-weight, swap any model without touching a rule. Every model call is logged and costed, and anything unresolved goes to a person.
Compared with the alternatives
| Approach | Reads messy documents | Proves each number | Same answer every time |
|---|---|---|---|
| Manual review | Yes, slowly | Sometimes | No |
| Rules-only software | No | Yes | Yes |
| Chat assistants and agents | Yes | No | No |
| SteadRail | Yes | Yes | Yes, for every rule in code |
Manual review is careful but slow. Rules-only software is consistent but breaks on messy documents. Chat assistants read anything but can’t prove an answer. SteadRail gives each part the job it does best: models read, code verifies, and every answer is cited. It runs in production today in our own commercial lending business.
In production, and what it can be set up for
Our own lending business. Borrower packages are read and cross-checked, and lenders are matched to each deal, with every figure tied to its page.
Ownership filings and registries checked against your foreign ownership, control and influence thresholds. An owner listed in one filing and missing from another gets flagged.
Applications, tax returns, financials and appraisals reconciled and checked against credit and covenant rules.
Technical manuals and maintenance logs matched to National Stock Numbers.
Connections to the systems you already run are scoped and built as part of each project.
Environments
| Environment | How it runs | Status |
|---|---|---|
| Your cloud account | Installed in your account, connected to the model endpoints your office has approved | Not yet deployed |
| Your own servers | Installed on your hardware, with open-weight models such as Llama or Mistral | Not yet deployed |
| Disconnected networks | Same as your own servers, with no outside calls | Not yet deployed |
| Our cloud | Our own commercial lending business | In production |
We have not deployed on a government network yet, and this table will say so until we have. SteadRail does not connect to GenAI.mil; it runs in your environment with the models your office approves. For government work we never host your data. Model calls go straight from your environment to your endpoint, so your data-retention terms carry over. Until the software is inside your boundary, we work only from blank templates and fictitious records.
Business model
Fixed price, paid by milestone. When it’s done, it’s yours to run. We’re seeking prototype funding to set it up for your mission.
We audit one of your workflows with your team.
The price follows the scope: how many document types, rules and systems we connect.
Built at a fixed price, paid by milestone on acceptance.
Installed in your cloud or on your servers, connected to your models. Yours to run, with no subscription.
Questions contracting officers ask
One common path is a prototype agreement under 10 U.S.C. § 4022, reached through a Commercial Solutions Opening or the Tradewinds Solutions Marketplace. If the prototype is awarded competitively and completed successfully, follow-on production can be awarded without further competition (§ 4022(f)). Write to us and we’ll work out the path with your contracting officer.
Two things: a model endpoint your office has approved, and access to the documents. Risk is managed in code: any model can be swapped, every output is checked, and people make the final call.
We expect SteadRail to qualify as a nontraditional defense contractor (10 U.S.C. § 3014). That would let a prototype agreement meet the statute’s cost-sharing condition without a one-third cost share (§ 4022(d)(1)(A)).
No. The harness runs in production in our own commercial lending business, and the founder’s companies have built their own software for nearly twenty years. We would rather tell you that here than have you find out on a call.
No. SteadRail installs in your cloud account or on your own servers, and model calls go straight from your environment to your endpoint. Until it’s inside your boundary, we work only from blank templates and fictitious records.
The ones you already use: a frontier model your office has approved, or an open-weight model such as Llama or Mistral on your own hardware. Each job goes to the model that fits it, and swapping a model doesn’t touch a rule. Every call is logged and costed.
A small team of U.S. citizens, working in the United States.
When it’s done, it’s yours to run: a permanent, royalty-free license, plus full rights to the rules and connectors built for you. The core harness stays ours, so we can keep improving it. No subscription.
The price follows the scope: how many document types, rules and systems we connect. We audit the workflow with you first, then quote a fixed price paid by milestone. No subscription, no per-seat fees.
Team
I’ve spent my career building companies and sitting on public-company boards, and my companies have built their own software for nearly twenty years. I’ve never sold to the government. I’m starting SteadRail because I love this country, and too much of the work that keeps it safe still comes down to someone reading stacks of paper by hand.
We’re a small American team. Our code is written here, by U.S. citizens. We’re new to federal work and we expect to earn trust one file at a time. If our software can’t show you the page behind an answer, it shouldn’t be making the call.
— Blake Janover, Founder
The team
Founder
3U.S. public listings as a principal: Janover Inc. (Nasdaq: JNVR) as founder and CEO, Soulpower Acquisition Corp. (NYSE: SOUL) as a founding director, and Deep Fission (Nasdaq: FISN) as a director.
Chief Architect
More than twenty years as a developer and entrepreneur, building commercial software on each new generation of technology, and AI since the first ChatGPT release.
Contact
Tell us the decision and the documents behind it. Every message goes straight to Blake.
desk@steadrail.com