Not an HMSThe revenue layer above the one you already run — orchestration for hospitals, health aggregation for employers.See the difference →

Nadi

Ask your own data. Get a number, not a paragraph.

Ctrl-K anywhere in Drapto. Every answer comes from your records with the query it ran shown underneath.

NADI · NADI
● Rules 24, rationale attached
● Sort by rupee exposure
● Runs before submission
✓ the intelligence layer

Nadi · the command bar

Press Ctrl-K. Ask your own data a question.

Not a chatbot in a corner. A command bar on every screen, which is a different thing: a chatbot is a place you go, and a command bar is something you press where you already are — mid-round, mid-claim, mid-argument with a payer.

Your pageRanks for your speciality and your city
You write400 words, checked by a second doctor
They book youAlready knowing why they are coming
You keep themFollow-ups raised and chased automatically
Ctrl Kwhat is at risk right now?
₹1,51,935

Earned in the last 90 days and not collected. ₹1,935 used and never billed, ₹1,50,000 denied with the appeal window still open, ₹0 past the window.

→ Revenue › Recovery — open the worklist
what is overdue in compliance?are we NABH ready? what equipment is due for service?which denials expire this week?

Figures shown are test-suite values. The link under every answer is the point of this page.

The command bar

Ctrl-K from any screen. It reads what you already have and shows you where the answer came from — it does not act on it.

The line that matters

She never invents a figure, and every answer links to the screen it came from.

Nadi answering a question with the figure, the rows behind it, and the query it ran
The answer, then the working. The query is shown every time — an answer you cannot check is a guess.

Every product in this category says “AI-powered”. Almost none of them will tell you what happens when the model does not know. In a hospital that question is not academic: an assistant that produces a plausible number is worse than no assistant, because somebody will act on it, and they will act on it faster than they would have acted on a spreadsheet.

What a generative assistant does

Produces an answer shaped like the right answer. When it does not know, it produces one anyway, in the same confident register as when it does.

What happens here

The arithmetic runs first, deterministically, over records already in your account. The model explains and prioritises what the arithmetic found. It is not the thing computing the number.

Which is why every answer carries a link to the screen it came from. Not a citation to a document — a link to the worklist, the register, the claim. If Nadi says ₹1,50,000 is recoverable, one click shows you the claim, the payer and the days left, and you can disagree with the screen rather than with the assistant.

The test to apply to any assistant, including this one. Ask it something your data cannot answer. If it produces a confident figure rather than saying the data is not there, you have learned everything you need to know about the numbers it gives you on the days you are not testing it.

Why a command bar and not a chatbot

The questions worth asking arrive while you are doing something else.

Nobody opens a chat window to ask whether the equipment is due for service. The question occurs during a round, in the middle of a different task, and the cost of leaving that task to go and ask is higher than the value of knowing. So it goes unasked, and the answer surfaces three weeks later as a problem.

On every screen

The same key, everywhere in the workspace. There is no page you have to navigate to first, which is the whole point.

It knows where you are

Asked from a claim, a question about “this patient” means that patient. Context is the difference between a command bar and a search box.

It answers, it does not act

Nadi shows you what is true and links you to the screen where you can change it. It does not submit claims, alter records or send anything on your behalf.

What it can answer

Twenty-six skills, across everything the workspace already holds.

Not the open web, and not medical knowledge in general. Your admissions, your claims, your contracts, your registers, your equipment, your schedules.

Claims at riskWhat is exposed, and why
Denials and appealsWhich windows close this week
Recovery worklistWhat is worth chasing today
Pre-authorisationClocks running, and on what
Room capsEligibility against the policy
Payer contractsTariffs and rate drift
Settlement advicesWhat was deducted and why
ICD-10 codingCodes, and unspecified ones
Documentation gapsWhat a claim is missing
NABH standardsWhich have no records
Compliance registersWhat is overdue
Equipment schedulesWhat is due for service
Admissions and bedsOccupancy and movement
AppointmentsLoad, gaps and no-shows
Corporate empanelmentEligibility and campaign uptake
Branch comparisonThe same question, across sites

Whose key, whose data

It runs on your AI key, which means you can switch it off.

Your provider, your model, your usage

The key is yours and encrypted at rest. You choose the provider and you see the usage, rather than paying us a margin on somebody else's inference.

Turning it off changes nothing else

Every other part of Drapto keeps working. An assistant that cannot be removed is a dependency, not a feature — and a hospital should be able to decide that separately.

Two more assistants share the same rule. Decoder reads a settlement advice for your billing manager, and Sahayak explains a rejection letter to a patient. Neither invents a figure either, and Sahayak will not predict the outcome of a claim.

What it will not do

The limits, because an assistant’s limits are the useful part of the spec.

No clinical advice. Nadi does not diagnose, does not suggest treatment and does not interpret results. It answers operational and financial questions about your own workspace.

No prediction dressed as fact. No recovery percentages, no likelihood that a claim will succeed, no NABH readiness score. Where an answer is an estimate, it says so; where the data is not there, it says that instead of filling the gap.

It does not act on your behalf. Nothing is submitted, altered or sent by Nadi. It shows you what is true and takes you to the screen where a person decides.

It is part of the paid product. The whole patient-facing half of Drapto is free forever; this is not in it.

Twenty-four answers with no AI key at all

24commands that are database queries, not model calls. They work offline
Ctrl-Kfrom any screen. A capability behind a panel is a capability nobody has
₹0extra. Bring your own key for free text, or run Ollama on your own hardware

What it is actually asked

What it is actually asked
You typeIt opens
who has not been readUnacknowledged lab results
who should I ring todayNo-show risk for tomorrow
what is unpaidCollections, oldest first
who has not come backOverdue follow-ups
No key needed for 24 skills
Your own Anthropic or OpenAI key
Or Ollama, on your hardware
Keys encrypted at rest
Every answer links to a screen
Nothing leaves for the built-ins

What we will never do

Things we have promised not to do

  • Take a cut of a consultation fee
  • Charge per appointment
  • Sell a position in the directory
  • Host star ratings
  • Move a free thing behind the paywall

How we are actually paid

  • Hospitals, for revenue integrity
  • Companies, for corporate health
  • Labs and pharmacies, for their modules
  • Implementation, because it is somebody’s week
  • Nothing from a patient, ever

One room or two hundred beds.

A solo doctor with one room
A clinic with three chairs
A 30-bed hospital billing insurers
A 200-bed group across branches
A company covering its staff
A lab or a pharmacy alongside

What runs without being asked

Improved most weeks
No AI key The waitlist

A cancellation is offered to the next person in order, with a window, until somebody takes it.

No AI key The follow-up chaser

Raised when the prescription is written, chased twice, then it stops. It does not nag.

No AI key Critical results

An abnormal value escalates after thirty minutes if nobody named has acknowledged it.

No AI key Claim risk

Twenty-four rules, scored before submission and sorted by exposure rather than raw risk.

No AI key Nadi, 24 commands

Ctrl-K from any screen. These are database queries, so they work offline and cost nothing.

Your key Free-text questions

Ask in your own words. Bring your own Anthropic or OpenAI key, or run Ollama on your hardware and nothing leaves the building.

We are deliberate about which is which. Most of what runs here is rules, not a model — because a rule is auditable, works when the connection drops, and cannot invent a figure. We build and improve both every week, and we will always tell you which one answered you.

Ask it something your reports cannot answer.

Ctrl-K, a question in plain English, and the query it ran shown underneath.

Twenty-four answers, no AI key.

They are database queries, not model calls — so they work offline and cost nothing. Bring your own key for free text, or run it on your own hardware.

app.drapto.com — Ctrl-K from any screen
who has not been read Ctrl-K NO AI KEY NEEDED — THIS IS A DATABASE QUERY 3 results flagged critical, unacknowledged for over 30 minutes Ramesh K · Potassium 6.4 · ordered 11:20 · nobody has opened it Anita S · Troponin 0.9 · ordered 09:05 · nobody has opened it

Twenty-four commands like this one. They are queries, so they work offline.

New

A page, not just a palette.

Ctrl-K is right for one question while you are on another screen. It is wrong for working something out over six, because the palette closes and takes the thread with it.

app.drapto.com/nadi
New conversation Search your conversations who has not been read 4 turns · 12m ago what is unpaid 2 turns · yesterday which communities are active 3 turns · Monday who has not been read 3 results flagged critical, unacknowledged over 30 minutes Ramesh K · Potassium 6.4 · ordered 11:20 Anita S · Troponin 0.9 · ordered 09:05 Database query · lab_unread · no AI key used which communities are active 1 active in the last thirty days Cardiology India · 412 members · 4 posts · 3 different people Database query · community_activity · no AI key used

Every answer says which of the two produced it. Nobody should have to wonder whether a figure came from their own database or from a model.

Conversations kept and searchable
Search by what was said in them
Twenty-six skills, no key needed
Every answer labelled at its source
Communities and activity included
Your data only, never another clinic’s