01 · Upload
Your deal documents
Offering memorandum, T-12 and STAR report. The files a seller asked you to keep confidential.
Asset ManagementUnderwritingMarket Intelligence
One shared record links every party from OM to exit. AI agents read the documents and do the busywork, and a calculation engine computes every number.
The founder underwrote at
Prior desks, not customers or endorsements. Built by Philip Bernardo, PATL’s founder.
PATL Studio · the hotel investment OS
Buy it, hold it, and know the market it sits in, without rebuilding the model at every handoff.
Agents read the OM, T-12 and rent roll and build the model. The engine computes every number.
In developmentHolds each hotel to the plan it was bought on, with actuals posted against the original underwriting.
Market data liveMarket data and performance forecasts by submarket, so every deal starts from the same view of demand.
Underwriting
Upload the OM. Agents pull the T-12, the STR report and the rent roll, and every figure sits beside the page it came from until a person approves it. Operations, debt, capex, stress and returns all seed from that one read.
Asset Management
Asset management usually starts over at closing, in a new spreadsheet that never reconciles with the underwrite. Here the acquisition model stays the plan, and monthly actuals post against it on the same record.
Market Intelligence
Pick the hotel out of the STR inventory and the market pull runs with the extraction: the submarket, the competitive set, seasonality and the federal economic panel, attached to the deal rather than pasted into it. Submarket performance forecasts are next.
How it works
Agents read OMs, T-12s and rent rolls, assemble the deal, run diagnostics and draft the review memo. Every figure they report comes from a deterministic Python engine they can call but never edit. Rerun it and the number does not move.
It works with the AI assistants your team already uses, so any of them can run a deal through PATL.
01 · Read
Agents extract the T-12, STR report and rent roll, each figure linked to its page. Nothing is trusted until a person approves it.
02 · Compute
Proforma, debt, capex, stress and returns populate from the same read. The agent calls the engine; it never writes a number itself.
03 · Share
The broker package, the credit memo and the variance report are views of the same run, so the lender reads what you built.
How PATL reads a deal
What happens, step by step, when you upload a confidential offering memorandum to PATL.
01 · Upload
Offering memorandum, T-12 and STAR report. The files a seller asked you to keep confidential.
02 · Read in private
An AI model trained on hotel documents reads every page on PATL’s own servers. No outside AI company sees your file.
On the roadmap03 · Calculate
Builds the proforma, sizes the loan and runs ten years of cash flow. Same inputs, same answer, every time.
Live today04 · Share
Every number links to the page it came from. Lenders and investment committees see the same file.
Live todayAll of this can run inside your own cloud account, under your own encryption keys.
On the roadmapSees only a tricky page, with names, addresses and deal terms blacked out first.
On the roadmapIn plain English: like a firm’s back office
Your own staff reads the file behind a locked door.
A specialist sees one blacked-out page, never the whole deal.
The accountant runs every number by the book and keeps the receipts.
TodayThe reading step runs on Anthropic’s Claude, under commercial terms that do not allow training on your files, and nothing it reads counts until a person on your team approves it. The private reader replaces that step. Anthropic is listed in our privacy policy.
PATLCalculator: live today · Private reader: on the roadmap
The product
A real offering memorandum goes in. A sized loan, a USALI proforma and a lender package come out, every figure traced to its source.
1:41 · captioned, no sound · Download MP4
What is in the engine
USALI
Rooms, F&B and other operated departments carry their own margins, and undistributed expenses sit where the standard puts them.
Franchise
Royalty is the small part. Marketing, loyalty and reservation fees come from a maintained database rather than a rule of thumb.
Debt
LTV, debt yield and DSCR solved together, with the constraint named on the output rather than left for you to work out.
Stress
RevPAR, expense and rate shocks run against coverage and equity, scored pass, warn or fail.
Exports
Two files your counterparty already knows how to read, both generated from the run rather than maintained beside it.
Provenance
Each extracted figure keeps a link to the document and page it came from, and to the person who approved it.
Start with underwriting
If the model reads it wrong, the fix goes in the engine, which is the part a support queue cannot do.