Data Rooms: turning a pile of records into something you can ask

“And when did your LDL start climbing?”

You're across from a cardiologist who asks, almost in passing, “and when did your LDL start climbing?” You know the answer is in a lab report. You know you have six of them: PDFs from two different labs, a photo of a printout, one buried in an email from last spring. You own every number the doctor needs, and you cannot answer the question.

That folder is what I've come to think of as the shoebox. Nearly everyone has one, and it isn't only medical: claims, contracts, statements, the letter that proves you disputed the charge. Cloud drives solved storing all of this a decade ago. What they store, though, is files. A folder doesn't add up your numbers, notice that a result is stale, remember that an appointment needs a referral letter, or draft the appeal for a denied claim. Every one of those jobs still lands on a person who is usually stressed, often unwell, and rarely an expert in the paperwork.

Even the newer “ask questions about your documents” tools hand the work back to you: you have to know what to ask, ask it well, and trust an answer you can't check. Data Rooms starts from a different premise. The software should do the reading itself, before you ask anything.

What happens when software reads the pile

In the prototype, a room is a bounded space for one area of your life—health, home, the business. You put documents in, and the room reads them into two things: structured data (the actual values, with units, linked to the document they came from) and a timeline of what happened when. Everything on screen is sample data from the demo room, built to make the interaction concrete; the numbers below are illustrations, not measurements.

The clearest artifact of that reading is the chart the demo room keeps on its overview. It isn't generated when you ask a question. It stands there, captioned with its sources, because the room has already read every lab report it holds.

Look at the source labels under the points. Two labs' PDFs, a photo of a printout, an email attachment. That mix is the honest shape of personal records, and it's also where a real version of this product would live or die. Pulling “LDL 142” reliably out of a crooked photo, and knowing it's LDL and not total cholesterol, in mg/dL and not mmol/L, is genuinely hard. The design's answer is to admit what it hasn't digested: the demo room shows 81 of 84 documents structured, with the three unread ones in plain view instead of quietly guessed at. A confident wrong number would be worse than an admitted gap. The chart also explains why the room can be trusted with the question at all: every point traces to a document you can open. The reading is the product.

Then it does the next piece of work

Reading is the foundation, and it's still only half the idea. The other half is that agents in the room carry the work one step further. In the demo, an explanation-of-benefits shows a denied physiotherapy claim, so the room drafts the appeal: it pulls the denial code from the EOB, cites the visit note and the referral that support the claim, and leaves a draft for you to review and send. The lipid panel predates the statin, so the room proposes a follow-up in June and can book it when you agree. A reminder from this room knows why it exists, and shows you the documents behind it.

Just as important is where the work stops. The room reads, structures, reminds, and drafts. It does not diagnose, and it does not send. “Your last panel predates the statin” is a scheduling observation grounded in a document; whether the number is worrying is the doctor's call, and whether the appeal goes out is yours. In the sprint we kept returning to that line, because software that acts on your medical paperwork is only tolerable if every action stops one step short of a decision that belongs to a person.

The same shape, three more shoeboxes

Fundraising. A startup's data room is the same pile wearing a suit: incorporation docs, the cap table, contracts, financials. Today founders assemble it by hand and then spend diligence answering questions whose answers are already in it. A room that has read its own contents can answer the investor's question directly (“what's the vesting schedule for the second founder?”), with the source document attached, while the founder sleeps.

Buying a house. Disclosures, the inspection report, loan estimates, insurance quotes. Every one has a deadline attached, and the buyer is the least experienced person in the transaction. A room that reads the pile can keep the deadlines, compare the loan estimates in one table, and flag the contingency you're about to let lapse.

Customer onboarding. Flip the direction: the room is what your customer shares with you. They drop in what they have; the room reads it against your intake checklist and tells both sides what's processed and what's still needed. Nobody emails a spreadsheet titled “final_v3” to anyone.

A folder can't tell you what's missing

The feature I'd defend hardest is the one that sounds smallest. In the demo, the room flags that cardiology wants a referral letter before the April appointment, and the letter isn't in the room. Search can only find what exists. Finding a gap requires knowing what a complete record should contain and comparing the pile against it—which is exactly the kind of judgment the reading makes possible.

Gaps are where the real money and the real risk sit. The missing IP assignment surfaces in diligence, at the worst possible moment, priced accordingly. The missing filing turns an audit from routine into adversarial. The missing referral letter turns a specialist appointment into a rescheduled specialist appointment, six weeks out. In each case the document you don't have matters more than the hundred you do, and a folder is structurally incapable of telling you about it. A room that has read everything can hold your pile against the checklist your situation implies, and say the quiet, valuable thing: you are almost ready, and here is the one item between you and ready.

What's in your shoebox?

Worth saying plainly: Data Rooms exists only as sprint screens, with no real users behind the sample room. Its job was to test a premise—that once agents can read a pile of documents into data and act on what they read, the useful product is the room, with its standing facts, its drafts, and its gap list. It's also a working example of the kind of software we describe in the bespoke SaaS post: designed from scratch around one real problem and what agents can now do with it, then run for the people who use it.

So here's the question worth taking back to your own shoebox, whichever one it is—the health folder, the deal room, the vendor-onboarding thread. Somewhere in your next appointment, audit, or closing, there's a document you'll be asked for. Would you know today if it's missing?