Cardinal · AI-Native Authoring Platform

From IB upload to 80-page protocol draft. In five minutes.

Merquell is the AI authoring platform for clinical trial protocols. We combine your Investigator's Brochure with structured precedent intelligence to generate ICH M11-compliant Phase 2 protocol drafts. Your medical writers refine — instead of recreating from scratch.

Cardinal
PROTOCOL DRAFT · ICH M11 · PHASE 2b
82Pages
ICHM11 Format
4:52Gen. Time
Draft complete — ready for medical writer review
Built on Anthropic Claude
SOC 2 framework in development
ICH M11 compliance built in
Multi-region (FDA · EMA · Health Canada)
8–12
Weeks of authoring time per Phase 2 protocol today
$200K
Average medical-writer cost per protocol
60%
Of protocol content is boilerplate, rewritten every time
450K+
Past trials available as precedent intelligence

The status quo is
costing you eight weeks.

Clinical trial protocols are still authored the way they were in 2005 — in Microsoft Word, passed between teams via email, rebuilt from scratch each time. The cost is measured in months of medical-writer time per protocol, and the loss is recoverable.

i.

Protocols start from blank documents

Medical writers spend the first two weeks searching for templates and adapting prior protocols — tribal knowledge that walks out the door when senior writers leave.

ii.

Boilerplate gets rewritten every time

Background, rationale, safety monitoring, and statistical frameworks are functionally identical across protocols, yet manually rewritten for each new study.

iii.

Precedent is locked in archives

Endpoint conventions, design patterns, and approved language live across thousands of past protocols. Until now, that precedent has been inaccessible at the moment of authoring.

A protocol draft
built on your data.

Upload your Investigator's Brochure. Provide 25 structured inputs covering design, population, and endpoints. In under five minutes, Cardinal — our AI authoring engine — returns a structured 80-page ICH M11-compliant draft with schedule of assessments, statistical framework, and safety monitoring sections intact.

  • Mechanism of action and PK/PD pulled verbatim from your IB — never fabricated.
  • Endpoint and design suggestions grounded in similar trials from ClinicalTrials.gov.
  • Editable Microsoft Word output that drops into your existing review workflow.
  • Built for the rigor of regulated clinical research — not a generic AI writing tool.
Cardinal · Generation Pipeline
Investigator's Brochure ingested · 47 fields extracted
0:32
Indication precedent loaded · 24 reference trials
1:18
Section structure planned · 18 sections
1:45
Schedule of Assessments generated
2:51
Statistical considerations drafted
3:34
6
Cross-section consistency check running...
4:12

Three steps. Five minutes.
An 80-page draft.

Cardinal is built around the workflow your medical writers already know — not a new paradigm to learn.

i

Upload your IB

Drop in your Investigator's Brochure. Cardinal extracts mechanism, dosing, PK/PD, and safety data — verbatim, never fabricated.

ii

Specify your study

Twenty-five structured inputs covering phase, design, blinding, randomization, endpoints, sample size, and population.

iii

Receive your draft

Editable Microsoft Word output, formatted to ICH M11, with section structure, SoA tables, and statistical framework intact.

Precedent Intelligence PHASE 2 · RA · MTX-IR
Endpoint suggestion
72% of recent Phase 2 RA trials in MTX-inadequate responders use ACR50 at Week 12 as primary. ACR20 use has declined to 14% since 2022.
High confidence
88%
Design pattern
Median sample size for similar Phase 2b JAK1-selective inhibitor trials: n=348 across 3 arms, with 1:1:1 randomization.
High confidence
92%
Safety framework
JAK inhibitor class typically defines 7 AESIs: serious infections, herpes zoster, MACE, VTE, malignancy, GI perforation, hepatic injury.
Class consensus
95%

Precedent intelligence,
at the moment of authoring.

Cardinal does not generate protocols from a blank slate. Every endpoint suggestion, design choice, and safety framework is grounded in the precedent of similar trials — surfaced from a structured index of past clinical research.

When ACR20 was the standard primary endpoint for Phase 2 RA trials, Cardinal would suggest it. Today, ACR50 has overtaken it — and Cardinal reflects that shift, with the data to back it up.

This is the difference between an AI tool that writes for you and an AI platform that thinks alongside you.

Built for the rigor of
regulated clinical research.

Cardinal is not a writing assistant. It is an AI-native protocol authoring platform — built from first principles around how clinical research teams actually work.

IB-grounded generation

Mechanism, dosing, PK/PD, and safety pulled verbatim from your uploaded Investigator's Brochure. Never fabricated, never approximated.

Available now

Precedent intelligence

Cardinal surfaces endpoint patterns, statistical approaches, and design benchmarks from past Phase 1–3 trials registered on ClinicalTrials.gov.

Roadmap · Q3 2026

Consistency checker

Catches cross-section contradictions before they reach review — treatment duration vs. SoA, endpoint definitions vs. statistical sections.

Roadmap · Q2 2026

Word-native export

Output is a properly formatted, section-structured .docx — not raw text. Drops into your existing review workflow from day one.

Available now

Collaborative workflow

Multi-user review, version control, and threaded comments for your full authoring team. No more emailing Word files between fourteen people.

Roadmap · Q3 2026

ICH M11 compliance

Protocol structure, section ordering, and terminology aligned to the ICH M11 guideline — the current international standard for clinical protocols.

Available now
"A protocol is not a document. It is the blueprint for a trial that could change patients' lives."

Merquell is an AI company building authoring tools for the world's most consequential documents — clinical trial protocols, regulatory submissions, investigator's brochures.

Today, these documents are still authored in Microsoft Word, passed around by email, and reviewed through processes built on tribal knowledge accumulated over decades. We exist to change that — not by replacing medical writers, but by amplifying them with AI built to the rigor of the science they produce.

Cardinal is our first product. Built from first principles, with input from medical writers and clinical operations leaders. We start with protocol authoring — and build toward a future where every step from IND preparation to regulatory submission has proper AI-native tooling.

Company

Merquell Technologies Inc., federally incorporated in Canada. Headquartered in Toronto, Ontario.

Stage

Pre-launch. Working with select design partners to validate Cardinal and shape the roadmap. Not yet generally available.

Target customers

Series A–C biotechs (20–150 employees) and clinical research organizations requiring Phase 1–3 protocol authoring.

Regulatory focus

ICH M11 compliant generation. US FDA, EMA, and Health Canada awareness built into the core architecture.

An AI platform built for
regulated industries.

Pharmaceutical-grade software requires more than a wrapper around a language model. Cardinal is engineered for the security, accuracy, and auditability that regulated research demands.

Anthropic Claude

Cardinal's generation engine is built on Anthropic's Claude — a state-of-the-art model designed with safety and accuracy as core principles.

Data security

Your IB and protocol inputs are encrypted in transit and at rest. SOC 2 Type II framework currently in development with target audit completion by Q4 2026.

Auditable output

Every generated section traces back to its source — IB extract, precedent reference, or user input. Designed for regulatory traceability from day one.

Multi-region ready

Built with awareness of FDA, EMA, PMDA, and Health Canada regulatory frameworks. Generation logic adapts to regional submission requirements.

Be among the first
to see Cardinal.

We are working with a select group of design partners — biotechs and CROs who want to shape an AI-native protocol authoring platform from the ground up. Request a walkthrough and we will be in touch within twenty-four hours.

A live walkthrough of the Cardinal protocol generation workflow
A sample draft generated for your indication and study design
Direct input into the Q2 2026 product roadmap
Founding pricing reserved for design partners only

No sales pitch. A thirty-minute walkthrough with the founder.

Request received.

We will be in touch within twenty-four hours to schedule your walkthrough. Watch your inbox for confirmation.