Decision owner
Medical monitor and study team
The named role remains accountable for the consequential decision.
Life Sciences & Pharmaceuticals
Designed for Clinical operations lead
Accelerate clinical trial protocol authoring by drafting sections from prior protocols, regulatory standards, and study assumptions while surfacing feasibility and patient-burden risks for the study team to resolve.
Contract LIF-02 · primary aggregate ProtocolDocument · mode loading
Decision brief
This brief starts with the decision, evidence, and accountable owner. The guided workflow then shows how the recommendation was produced.
The evidence and control points that shape this recommendation.
Decision owner
Medical monitor and study team
The named role remains accountable for the consequential decision.
Governed evidence
5 record types
Structured records and cited text ground the recommendation.
Workflow
5 controlled stages
Each transition records its input, output, status, and audit context.
Human controls
1 approval gate
Approval gates prevent the copilot from making consequential decisions.
For a phase 2 study in heart failure the copilot drafts objectives and eligibility from two precedent protocols, cites the applicable statistical guidance, models that the creatinine exclusion removes 38 percent of the eligible population, and the medical monitor relaxes the threshold before releasing version 0.4 for ethics submission..
Accelerate clinical trial protocol authoring by drafting sections from prior protocols, regulatory standards, and study assumptions while surfacing feasibility and patient-burden risks for the study team to resolve.
Released protocol version for review board submission gives Medical monitor and study team the evidence needed to begin the final governed business outcome, with the decision trail retained for review.
Step 1 of 5
| Field | Value |
|---|
| Field | Value |
|---|
The output appears here immediately. More technical evidence remains available below.
The demonstration keeps deterministic controls, AI assistance, and approval separate.
Source systems enforce identity, workflow order, policy filters, and record updates.
Retrieval and generation assemble relevant evidence into a cited recommendation or draft.
Medical monitor and study team verifies material claims and approves the consequential action.
Run the stages in order before using the Copilot. Every stage explains what happens, why it matters, the evidence it uses, and the complete API request and response.
Automated stage
What happens: Clinical operations lead performs define study assumptions and comparators using Indication, phase, endpoints, and prior study references and produces ProtocolDocument shell with assumption set. The transition is deterministic and does not require autonomous model approval.
Why it matters: ProtocolDocument shell with assumption set gives Retrieval agent the evidence needed to begin Retrieve precedent protocols and standards, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/define-study-assumptions-and-comparators
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Retrieval agent performs retrieve precedent protocols and standards using Indication and phase filters and produces Precedent sections and applicable guidance clauses. The transition is deterministic and does not require autonomous model approval.
Why it matters: Precedent sections and applicable guidance clauses gives Authoring agent the evidence needed to begin Draft protocol sections with lineage, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/retrieve-precedent-protocols-and-standards
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Authoring agent performs draft protocol sections with lineage using Precedents, standards, and assumptions and produces ProtocolSectionDraft set with source lineage. The transition is deterministic and does not require autonomous model approval.
Why it matters: ProtocolSectionDraft set with source lineage gives Feasibility analytics service the evidence needed to begin Model feasibility and patient burden, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/draft-protocol-sections-with-lineage
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Feasibility analytics service performs model feasibility and patient burden using Eligibility criteria and visit schedule and produces FeasibilityAssessment with recruitment estimates. The transition is deterministic and does not require autonomous model approval.
Why it matters: FeasibilityAssessment with recruitment estimates gives Medical monitor and study team the evidence needed to begin Study team review and version release, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/model-feasibility-and-patient-burden
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Human approval required
What happens: Medical monitor and study team performs study team review and version release using Drafted protocol with feasibility findings and produces Released protocol version for review board submission. A named human approver must review the evidence before the transition completes.
Why it matters: Released protocol version for review board submission gives Medical monitor and study team the evidence needed to begin the final governed business outcome, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/study-team-review-and-version-release
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Run a stage to see its explanation, evidence, full request, and full response.
Ask a question and receive an answer grounded in retrieved ProtocolDocument evidence.
Select a starter question or enter your own.
Loaded live from /api/config, /api/domain/model, and
/api/domain/sample.
protocolDocuments/tenantId + /studyIdFor a phase 2 study in heart failure the copilot drafts objectives and eligibility from two precedent protocols, cites the applicable statistical guidance, models that the creatinine exclusion removes 38 percent of the eligible population, and the medical monitor relaxes the threshold before releasing version 0.4 for ethics submission.
| Container | Role | Hierarchical partition key | Document types |
|---|---|---|---|
protocolDocuments |
Primary | /tenantId + /studyId |
ProtocolDocument, ProtocolSectionDraft, EligibilityCriterion, FeasibilityAssessment |
regulatoryStandardsLibrary |
Reference | /tenantId + /standardId |
RegulatoryStandardClause |
| Type | Container | Partition key | Identifier pattern | Embedding fields |
|---|---|---|---|---|
ProtocolDocument |
protocolDocuments |
/tenantId + /studyId |
protocol::{studyId} |
None |
ProtocolSectionDraft |
protocolDocuments |
/tenantId + /studyId |
section::{studyId}::{sectionCode}::{draftVersion} |
sectionVector |
EligibilityCriterion |
protocolDocuments |
/tenantId + /studyId |
criterion::{studyId}::{criterionId} |
criterionVector |
RegulatoryStandardClause |
regulatoryStandardsLibrary |
/tenantId + /standardId |
standard::{standardId}::{clauseRef} |
clauseVector |
FeasibilityAssessment |
protocolDocuments |
/tenantId + /studyId |
feasibility::{studyId}::{assessmentId} |
None |
Read the current draft of every section for the study in one partition query.
protocolDocuments
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.studyId = @studyId AND c.type IN ('ProtocolDocument','ProtocolSectionDraft') ORDER BY c.sectionCode ASC
Find eligibility criteria whose modelled screening impact is severe.
protocolDocuments
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.studyId = @studyId AND c.type = 'EligibilityCriterion' AND c.screeningImpactEstimate > @impactThreshold ORDER BY c.screeningImpactEstimate DESC
Knowledge-container query against regulatoryStandardsLibrary (bounded fan-out across the /tenantId + /standardId partitions named by the shortlist): retrieve the clauses in force for the standards that govern this study, fanned out across the small fixed set of applicable standard ids.
regulatoryStandardsLibrary
partition-key-fan-out
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.standardId IN (@applicableStandardIds) AND c.type = 'RegulatoryStandardClause' AND ARRAY_CONTAINS(@studyJurisdictions, c.jurisdiction) ORDER BY c.clauseRef ASC
List sections carrying unresolved authoring issues before version release.
protocolDocuments
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.studyId = @studyId AND c.type = 'ProtocolSectionDraft' AND ARRAY_LENGTH(c.openIssues) > 0 ORDER BY c.authoredUtc DESC