Start here

Starting a study

What the platform needs from you, what it works out for itself, and what happens between the moment you press Confirm and the moment a verdict appears.

A feasibility run starts from whatever you already have. If you have a protocol, upload it. If the protocol does not exist yet, an indication and an intervention are enough to get a public-data read on whether the trial is worth designing at all.

Nothing you upload is used to train a model, and nothing is published. The run reads public records and grounds every number it produces in one.

What you need before you start#

The engine works from the study definition, not from patient data. You never need to send us Protected Health Information to get an assessment.

The indication
The disease or condition being studied. This is the single most load-bearing input — it anchors the epidemiology, the competitive trial landscape, the regulatory precedent and the market sizing.
The intervention
The molecule, biologic or device under study. If the molecule is unnamed or pre-clinical, a therapeutic class is enough to run the commercial pillar.
Anything else you have
Phase, endpoints, eligibility criteria, planned sample size, planned countries. Each one you supply replaces a modelled assumption with a stated fact, and the assessment marks which is which.

You do not need a final protocol. A synopsis, a registry record, or a one-page concept is enough to run the public-data assessment — the parts you have not decided yet are modelled and labelled as assumptions rather than guessed at silently.

Uploading the protocol#

Documents are the fastest way in. Drop the protocol — or the synopsis, the investigator brochure, the registry record — into the workspace and the platform reads the study definition out of it.

  1. Upload the document

    PDFs and text documents are ingested, chunked and indexed against your workspace only. They stay private to your tenant.

  2. A draft study appears

    The platform extracts the indication, intervention, phase, endpoints and eligibility criteria and creates a draft study from them. Nothing has been run yet — a draft costs you nothing.

  3. Check what it read

    Open the draft and correct anything the extraction got wrong. This is the cheapest possible moment to fix an input: every downstream number depends on it.

  4. Confirm

    Confirming is the gate. One click promotes the draft to a live study and launches the full public-data pull plus every pillar analysis.

What happens during the run#

Confirming fans the study out across the live public-data connectors — trial registries, literature, regulatory and pharmacology databases, patents, pricing and financial filings — and then computes the analyses on top of what came back.

You can watch it happen. The study surface shows the run progressing rather than a spinner, and the evidence ledger records honestly which connectors returned data and which did not.

  • Assessment tabs stay locked until the data pull has produced something for them — a locked tab is the product refusing to show you an empty analysis dressed up as a result.
  • The Verdict tab is always reachable, and reads as pending until the pillars beneath it have landed.
  • A connector that returns nothing is recorded as returning nothing. It is never silently replaced with an assumption.

When the run finishes#

You get a six-pillar assessment ending in a go/no-go recommendation, with every figure carrying its citation and its evidence band. From there the expert-role workspaces turn the assessment into the documents the decision actually needs.

  • Read the assessment pillar by pillar, or start at the verdict and work backwards through what drove it.
  • Hand a pillar to the relevant expert role to draft a deliverable — a Go/No-Go memo, a protocol synopsis, a statistical analysis plan.
  • Sign off the deliverables you accept, with a 21 CFR Part 11 electronic signature that pins the exact evidence you reviewed.

Related

Next

Start here

Reading an assessment

The six pillars, the questions each one answers, and how to tell a number backed by several independent sources from one resting on a single record.

Open

The evidence

Where the numbers come from

Around fifty live public-data connectors, seven of them load-bearing, each pinned to the snapshot it was read from — and an honest ledger of the ones that returned nothing.

Open

Your team

Expert roles & sign-off

Seven expert workspaces draft the documents your decision needs; your team reviews them and signs with a Part 11 electronic signature that pins the evidence it was based on.

Open

See a verdict you can actually check.

Send us a protocol — or just a molecule and an indication. We'll return a fully cited feasibility assessment you can trace, line by line, back to public data — yours to defend in a bid, take to your board or investment committee, or hand to a regulator.

Book a demoSign in