The science is already done
Trials, prices, patient counts and claims data sit in spreadsheets and source files.
Pramana by VedAGI, for US market access teams
Drug and device companies already have the model and already use AI to write the dossier. Pramana makes sure every number that reaches a payer was computed from source, labeled honestly, signed by a person, and can be checked by the reader.
Pramana is Sanskrit for proof: a means of valid knowledge.
Example numbers only. Pramana blocks the pack and people fix it. It never quietly edits a figure.
The idea
Teams already build the model and already use AI to write the pack. The number then hides inside the writing, a person signs it anyway, and the other side cannot check it.
Pramana recalculates each number from source, marks guesses as guesses, refuses to release until a person signs, and gives the other side a receipt they can open in a browser. Same pack. Same model. The leak is closed.
The path
A company has a drug, biologic or device and wants health plans to cover it. There is no single national reviewer, so the same numbers travel to many readers.
Trials, prices, patient counts and claims data sit in spreadsheets and source files.
Usually Excel or a specialist tool: a budget impact model and a cost-effectiveness model. It should be the one true source.
An AMCP dossier 8, plus a pre-approval (PIE) deck, payer slides, a budget calculator and, for Medicare-negotiated drugs, data for CMS.
Often by an AI assistant now. One team estimated AI cuts first-draft time by about 40% 4. Faster writing means more numbers to check.
Medical, legal and regulatory reviewers approve it and a named person signs. They trust the numbers match the model.
To PBMs, health plans and P&T committees, often when they ask for it. Copies live on in slides and field decks.
P&T committees vote. PBMs negotiate. ICER may publish its own model. CMS reviews data the company certified.
Canadian public coverage runs through a few national bodies. The US has many separate payers, and three PBMs processed 80% of prescription claims in 2025 1. One number, copied into many documents, is read by all of them.
The gap
The weak joint is not whether AI can write. It is that whoever writes each sentence can copy, round, or quietly change the number inside it. In the US that happens across many documents at once.
One figure lives in five or more documents. A hand edit or an AI rewrite changes one copy and not the others.
An uptake assumption reads like hard data because nothing marked it as an estimate.
MLR reviewers check claims and wording. They cannot recompute every figure from source before signing.
When a P&T member, ICER or FDA asks to see the working, teams dig through emails and old spreadsheets.
Economic information sent to payers must rest on competent and reliable scientific evidence, and if FDA asks, the company must provide the primary data and analysis. A June 2026 revised draft brings devices in 5.
For Medicare drug price negotiation, the company certifies its data are complete and accurate, and must send corrections if they are not 6.
ICER builds its own models and shares them with manufacturers under a transparency program, so your numbers get compared with theirs 7.
The industry already has models, writers and signers. It does not have a gate that says: this number was computed, labeled, signed, and can be checked by a stranger. That gate is the gap. Pramana is only that gate.
The gate
Keep the model. Keep the writer. Keep MLR review. Pramana sits between “the words are drafted” and “the pack is signed and sent”, and it watches every copy.
Each figure is computed again, in code, from the company's own sources. The AI may suggest a formula. It never writes the value.
If a number is an assumption, it is marked as one in every document it appears in. It cannot pass as a measured fact.
The dossier, PIE deck, payer slides and calculator must all match the locked figure. If one does not, nothing goes to MLR or out the door.
What was computed, from which sources, with which formula, signed by whom. Payers open it in a browser, with no VedAGI account. The same record answers an FDA or CMS request.
One number
Follow a single figure, the year-one cost per member per month for a commercial health plan, from the company's files to a P&T reviewer's screen.
Pramana reads the company's own files: trial data, prices, claims-based patient counts and the model. Nothing new is invented.
The AI can propose how the number should be worked out. Pramana runs that formula itself, in code, on the real inputs.
The computed value is checked everywhere it appears: dossier, PIE deck, slides, calculator. Any mismatch is flagged.
Computed from measured sources, it becomes a figure. Built on an assumption, it stays a labeled estimate that everyone can see.
Reviewers approve computed figures, not paragraphs. Pramana records who signed and when.
Value, unit, formula, sources, time and signer, in one page any payer can open.
Locked. Anyone can recheck this number.
Example receipt. Values are illustrative.
Value
Pramana does not make a product look better. It saves the hours spent chasing numbers and protects the launch from avoidable slips. Anything we estimated is marked as an estimate, the same rule Pramana applies to its own numbers.
How we got this: About 40 key numbers, each repeated in about 5 places (dossier, PIE deck, payer slides, calculator, summary), makes 200 spots. At about 10 minutes each by hand, that is about 33 hours per review round, times 3 rounds. Team time valued at $150 to $250 an hour. FDA expects payer information to be updated when it goes out of date, so this repeats with every refresh 5.
~$500K
average drug sales per day of delay 3
This is an average across many drugs. It is sales, not profit, and one plan's decision is only a slice of it. Many P&T committees meet on a set schedule, often quarterly, so the 90-day case is an assumption. The point is scale.
| Question | Locked before it leaves | Corrected after someone else finds it |
|---|---|---|
| When the error is found | Inside the company, before MLR sign-off | After payers, ICER or FDA have already seen it |
| Who finds it | Pramana flags it automatically | A P&T reviewer, a PBM analyst, or a regulator |
| What it costs | A few hours to fix a flagged number | Delayed coverage, tougher rebate talks, stricter access rules |
| What you can say | “Here is the receipt for every number.” | “We will look into it and get back to you.” |
We will measure, not guess. The first engagement locks one live results table and every copy of it, and records the real hours before and after. Those measured numbers replace every estimate here.
Who it helps
Each person who touches the number gets something different.
They approve computed figures, not paragraphs. If a number cannot be locked, it does not go out.
They keep the model they trust and stop chasing numbers across five documents.
A wrong number in front of a PBM or P&T committee can delay coverage, weaken rebate talks, or lead to tighter access rules.
They can check the receipt without buying anything. Trust moves from “we like this company” to “we can recompute this.”
A ready record for FDA's evidence standard and CMS data certification: sources, formula, value, signer, release.
Limits
Pramana does not:
If the model is wrong, the lock will faithfully lock the wrong math. The benefit is integrity of release, not a better economic answer.
Start
Lock the budget impact table in one live AMCP dossier, and every copy of it in the PIE deck and payer slides. You keep your model and your MLR process. We measure the hours saved, and those measured numbers replace every estimate on this page.
Time and money figures marked as estimates are illustrative and will be replaced by measured results from the first engagements. Nothing on this page is legal or regulatory advice. Looking for the other market? Read the Canada edition.
If you are about to send a table you cannot recompute, talk to us.
VedAGI. Intelligence for Humanity.