AN Alpesh Nakrani
SolutionsBlogBooksPraiseAbout Work with me ↗
Healthcare · Growth

Clinical trial matching that saves coordinator hours.

Screen candidate patients against protocol criteria with cited evidence, explain uncertainty, and prepare a coordinator review queue.

◆ human-gateda person approves every consequential action
$18,500
fixed-scope pilot
Specialist opportunity
launch posture
Emerging specialist demand
market signal
clinical-trial-matching-assistant
// normalize criteria
input: Protocol inclusion/exclusion criteria
step: retrieve patient evidence
citations: [ source ✓ ]   confidence: 0.93
HUMAN GATEawaiting review →

Nothing is finalized until a human approves it.

Built for
The buyer
Chief Research Officer, site-network CEO, VP Clinical Operations
The champion
Research Program Director, Trial Recruitment lead, Principal Investigator
Day-to-day users
Research coordinators, investigators, patient navigators

Designed, built, and evaluated by Alpesh Nakrani, VP of Growth at ViitorCloud, 14 years shipping software, writing on AI-Native engineering and evaluation.

Evals-first
built in from day one
Human-gated
judgment stays with you
The problem

Where the time and money actually go.

Eligibility criteria are complex, chart data is incomplete, coordinators manually search records, and potentially eligible patients are missed or contacted too late.

Who feels it

Research coordinators, investigators, patient navigators

Trigger to act: A research site has under-enrollment, multiple active protocols, feasibility pressure, or wants to scale prescreening without replacing investigator judgment.

Outcome & ROI

The result you can model before you sign.

Illustrative, replace with your data
$10,500
per month, illustrative

Illustrative only: 10 active studies × 25 coordinator hours/month saved × $42 loaded hourly cost = $10,500 monthly capacity. Enrollment value is protocol-specific and must not be assumed.

The outcome, plainly: Screen candidate patients against protocol criteria with cited evidence, explain uncertainty, and prepare a coordinator review queue.

Coordinator-review precision
Recall on known eligible cases
Unknown-criterion rate
How it works

Inputs in. A cited, review-ready result out. Your expert decides.

A Permission-aware RAG copilot. Every material fact is grounded in an allowed source and returned with its identifier, with no invented data.

01
Normalize criteria
02
Retrieve patient evidence
03
Produce match / no-match / unknown per criterion
04
Rank candidates
05
Identify missing tests
06
Create coordinator summary
07
Document provenance
Reference architecturegrounded · human-in-the-loop · fully auditable
Source systems · scoped access
CTMS
EHR / data warehouse
Protocol repository
IRB-approved outreach workflow
Patient consent / contact controls
Grounded reasoning core
Retrieve & extract
grounded on your sources, returns citations
Reason & draft
Claude Sonnet 4.6 or GPT-5.6 Terra
Human gateResearch staff and the investigator determine eligibility and authorize contact; uncertain or sensitive criteria never resolve automatically.
Action · only after approval
Document provenance
Audit trace
sources, rules, confidence, reviewer
Tenant isolation
minimum data, never cross-tenant
Evaluation suite
baselined pre-launch, watched after
Observability
cost, latency & drift telemetry
Model strategy

Claude Sonnet 4.6 or GPT-5.6 Terra for complex grounded work; select by task-level evaluation; Gemini 2.5 Flash, GPT-5.4 mini or Claude Haiku 4.5 for high-volume routing and drafting. PostgreSQL + pgvector or managed vector store; Policy rules and evaluator service.

Inputs
  • Protocol inclusion/exclusion criteria
  • Structured clinical data
  • Notes
  • Labs
  • Medications
  • Diagnoses
The human gate

AI-Native, not autonomous. Judgment stays with your people.

The machine does the work; the human’s role narrows to the one thing that matters, judgment. That constraint is what makes it safe to deploy.

Non-negotiable human gate

Research staff and the investigator determine eligibility and authorize contact; uncertain or sensitive criteria never resolve automatically.

What it will never do
No final eligibility determination
No patient contact without IRB-approved process
No use outside approved protocol/data permissions
No promise of enrollment outcomes
The scorecard

A scorecard, not a demo. We baseline what breaks in production.

Every deployment ships with an evaluation suite. These are the numbers we baseline before launch and monitor after.

Primary
Coordinator-review precision
Recall on known eligible cases
Unknown-criterion rate
Screen-to-consent conversion
Time to candidate list
Provenance accuracy
Privacy incidents
Why this, not that

The category is crowded. Most of it isn’t built for your workflow.

The alternatives
Deep 6 AITriNetXTrialXMendel.aiTempusCTMS vendorsManual chart screening
This implementation

Fixed-scope, tuned to your systems and rules, grounded in your data, with the human gate and audit trail built in from day one. A price you own, not a subscription you rent.

✓ Fixed price, not a seat subscription ✓ Grounded in your data & rules ✓ Human approval on consequential actions ✓ Auditable decision trace
Systems & integrations

It plugs into the stack you already run.

No rip-and-replace. Access is scoped to the minimum data necessary, isolated per tenant, and fully logged.

CTMSEHR / data warehouseProtocol repositoryIRB-approved outreach workflowPatient consent / contact controls
Pricing

Transparent by design. The build price buys the workflow and the proof.

A fixed implementation fee plus a monthly bill that scales with volume and governance. No hidden seats.

Pilot
$18,500
one-time · bounded proof of value
  • One process / scope
  • Live workflow on your data
  • Baseline evaluation suite
  • Measured vs. current process
Most chosen
Production
$43,000
one-time · full deployment
  • Full scope & integration
  • Human-review UI & audit trail
  • Write-back to your systems
  • Production evals & monitoring
Enterprise
$72,000
one-time · multi-entity / regulated
  • Multi-facility rollout
  • Advanced security & compliance
  • Custom control & escalation
  • Dedicated evaluation program
Monthly operating cost

10,000 to 35,000 grounded questions per month plus indexing and vector search.

$500–4,200
usage (models, OCR, vector, storage)
$2,800/mo
managed evaluation & monitoring

Planning assumptions, not vendor quotations. Your CTMS and other platform licenses are separate and owned by you. Figures confirmed during scoping.

On working with Alpesh
“His vast knowledge of technologies and a natural problem-solving mindset consistently lead us through complex challenges with clarity and confidence.”
AM
Adil Multani
Senior Backend Developer
Why this is safe to try
01Baseline first. We measure your current numbers before we build anything.
02Fixed scope, fixed price. One process in the pilot. No open-ended engagement.
03Expand only if the scorecard earns it. You see the measured result before committing to production.
04Your people stay in control. The human gate means nothing consequential happens without a human’s approval.
FAQ

Questions serious buyers ask.

Does the AI act on its own?

No. Research staff and the investigator determine eligibility and authorize contact; uncertain or sensitive criteria never resolve automatically. The system drafts and recommends; a human approves every consequential action. Explicitly excluded: No final eligibility determination; no patient contact without IRB-approved process; no use outside approved protocol/data permissions; no promise of enrollment outcomes..

How do you stop it inventing facts?

Every material claim is grounded in an allowed source record and returned with its source identifier. The system separates observed facts, model inference, and missing information, and routes to a human whenever confidence is low, evidence conflicts, or an adverse outcome is possible.

What does it cost to run each month?

A usage bill of roughly $500 to $4,200 per month (10,000 to 35,000 grounded questions per month plus indexing and vector search), plus a $2,800 per month managed retainer for evaluation, monitoring and maintenance. Your existing platform licenses are separate and already yours. Exact figures are confirmed during scoping.

Do we need a ChatGPT or Claude subscription?

No consumer ChatGPT or Claude subscription is required for the production workflow. The client needs an approved API/cloud billing account. Workspace seats are optional for internal prototyping and administrator access.

How is this different from Deep 6 AI?

Tools like Deep 6 AI, TriNetX, TrialX are broad platforms you adapt to. This is a fixed-scope implementation tuned to your systems and rules, grounded in your data, with the human gate and audit trail built in, and a transparent price instead of a seat subscription.

How long until it is live, and how do we prove it works?

This is a specialist opportunity. We baseline “Coordinator-review precision” first, then measure against that baseline. You see the scorecard before expanding scope: the evaluation suite ships with the system, not as an afterthought.

Book a scoping call

Bring your real numbers. Leave with a fixed-scope plan.

A 30-minute engineering-led working session, no slideware. You leave with a sized opportunity estimate, a fixed-scope pilot plan, and the integration & human-review path mapped.

VP of Growth at ViitorCloud · senior delivery owner confirmed before paid work

Ask AI about Clinical Trial Matching Assistant