Draft study-report sections, protocol text and narratives from the locked dataset and your own templates, with numbers tied to the outputs they came from — the medical writer and the study statistician approve.
Take the locked dataset version, the tables, listings and figures approved for it, and the analysis plan behind them.
02
Read the document template, the previous draft of each section and the wording the study already carries.
Reason
03
Draft each section into your own template, to the content the guideline prescribes for that section.
04
Bind the numbers and statements in the text to the table, listing or figure they were taken from.
05
Compare the dataset version in scope with the one the last draft was written from, and mark what moved.
Decide
06
Hold text whose figure no longer matches its source, and wording carried in from a template or a prior study.
07
Route interpretation, the choice of analysis and anything the outputs do not carry to the writer and statistician.
Out
08
Present the drafted section beside its outputs, the version it was written from and what changed since the last draft.
09
Retain the source of each figure quoted, the template used, the reviewer edits and the version behind the draft.
→Product statement
The agent drafts and traces inside the approval boundaries agreed during implementation. Interpretation, the conclusion, the choice of analysis and approval of a report, protocol or amendment stay with your writer, statistician and medical lead; the sponsor answers for the filing.
Example workflow
One report section, end to end
AgentHuman
1Section openedThe reporting plan after database lock, an amendment, or a question the medical lead has raised
2Sources resolvedDataset version, the outputs approved against it, the analysis plan in force and the section template
3Section draftedWritten into your template, each number and statement carried from the output it was read out of
4Controls appliedNumber-to-output checks, prescribed-content checks, carry-over checks, version comparison and confidence threshold
No human action required
Stages 1 to 4 run without a person in the loop — drafting and the source checks finish first, because a section whose figures have not been checked wastes the review it goes into.
5DecisionSplits on the source checks and the confidence threshold
Figures agree with their outputs
Joins the pack the reviewers read.
A figure or a claim will not source
Held beside the output it disagrees with.
Writer and statistician review
The section is held beside its outputs, the dataset version it was written from and the text the agent could not source.
Accept · Rewrite · Query the statistician
Accepted — handed back▼
6Draft joins the review packWritten to the document system only where access and approval policy allow; nothing is approved or signed
7Outcome evaluatedSource-check failures, text the writer rewrote, prescribed content missed and what the statistician sent back
Rewrites
Lines the writer rewrote before the pack went out are counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Approving or signing a study report.
Approving a protocol or an amendment.
Interpretation, and any conclusion about a result.
Choosing which analysis a section presents.
Automation boundaryAgent acts unaided
✓Draft each section into your template, to the prescribed content.
✓Bind each number in the text to the output it came from.
✓Compare dataset versions and mark what moved.
✓Hold unsourced text and carried-over wording for the writer to read.
Write actions run only inside the approval boundaries agreed during implementation. Signing a report is not one of them.
Any comparative or off-label statement.
Changing a number so the text agrees.
Deciding a prescribed section element does not apply.
Changing templates, drafting rules or the dataset in scope.
Example output
One drafted section, annotated
Everything the agent writes is attached to the output and the dataset version it was read from.
Drafted section · single study reportIllustrative example
Document
Section
Dataset
Draft handed to
Confidence
Held for
Clinical study report
Adverse-event summary
Lock 2, current
Writer, unapproved
93%
A figure from lock 1
As receivedThe document, the section and the dataset version the reporting plan puts in scope.
Why it stops hereA figure traces to a table from the previous lock, so the text is held, not edited to agree.
ActionAcceptRewriteQuery the statistician
What the score decidesConfidence sets how closely the writer reads it, not whether a figure is right.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
Every section in the planFrom the reporting plan after lock
03Drafting & tracing
Keep the text tied to the outputs
Use the approved template, the analysis plan and the outputs produced against this dataset version.
01Approved path
Stop re-keying numbers by hand
Each figure in the text arrives with the table, listing or figure it came from, at the version it was read at.
02Human review
Make carried-over text visible
Wording reused from a template or a prior study, and text no output supports, are marked in the draft rather than reading like the rest.
04Build an evidence trail
Retain the dataset version, each figure's source output, the template used, the confidence, the evaluator result and every reviewer edit — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Authoring & templatesMicrosoft Word · Veeva Vault RIM Template and style libraries · SharePoint
Statistical outputsTFL packages · define.xml SAS and R outputs · analysis metadata
Study dataADaM and SDTM datasets · data-lock records Medidata Rave · Veeva CDMS
Agent
Medical writing & CSR authoring
Drafts the section Traces each figure Holds unsourced text
Cohorts here are document types, not studies. The number is drafted lines a writer rewrote or a statistician sent back — narratives written from documents that disagree, and re-locked sections carrying the last draft's figures.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Serious-event patient narratives
3.9%
2.5×
Review
Sections redrafted after a re-lock
3.4%
2.2×
Review
Text reused from prior studies
2.5%
1.6×
Watch
Routine template-led sections
1.4%
0.9×
Normal
Bar: corrected-line lift vs. template-led baseline · scale 0–4.0× · tick at the 2.0× threshold2 of 4 slices over threshold
Evidence-linked improvement
Two drafts of the same section should not fail the same way
A line the statistician sent back points at the source map, the template or the number check behind it. The change goes there, before the next section.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
One document cohort's corrected lines move away from the rest.
02Diagnose
These live in the step between an output and a sentence.
03Improve
The source map, template or check moves through your change control first.
04Verify
Sections that failed are written again from the dataset version in force.
05Learn
The corrected line is kept, and the wording the writer chose sits in the template.
Learn → DetectThe return edge. A report already approved is not quietly re-cut — the change is recorded and reaches the next draft a writer opens.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, templates and outputs, drafting and source binding, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and boundary definition.
02Document set, templates and section map.
03Dataset version and output-package access.
04Source binding from text to table, listing or figure.
05Section drafting into your own template.
06Narrative drafting from case documents.
07Carry-over and prior-study text checks.
08Version comparison and change marking.
09Writer, statistician and medical lead review workflow.
10Evaluation suite and regression sections.
11Document-system integration and traces.
12Deployment, documentation and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them. No tier lets the agent approve a report or decide what a result means.
Capability✓ in scope · — not at this tierPilotOne document, one studyProductionProduction document-system integrationAdvancedSeveral studies and document types
Introduced at Pilot
Sections drafted into your templates✓✓✓
Figures bound to their source output✓✓✓
Dataset-version comparison✓✓✓
Carry-over and prior-study checks✓✓✓
Writer and statistician review✓✓✓
Baseline evaluation✓✓✓
Patient narratives from case documents✓✓✓
Introduced at Production
Document-system integration—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Several studies and document types——✓
Translation and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on the documents and studies in scope, template complexity, output and dataset access, document-system integration, approval controls and deployment requirements.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01The document set and the template each section is written into→Document set, templates and section mapWeek 1
02Who owns each section and who approves the finished report→Approval-boundary definition and the review workflowWeek 1
03Access to the locked datasets and the output packages→Dataset version and output-package accessWeek 2
04The analysis plan and what was prespecified in it→Source binding from text to table, listing or figureWeek 2
05Case source documents for the narratives in scope→Narrative drafting from case source documentsWeek 3
06The sections your writers rewrote most on the last study→Evaluation suite, regression sections and failure-mode testingWeek 4
07Named writers, a study statistician and a medical lead→Review workflow, then pilot sections and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Source binding is built in week 2, because every check after it reads against that map.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Boundary, document set and the sections in scopeW2Template mapping, dataset access and source bindingW3Drafting into your sections, and the first narrativesW4Version comparison, carry-over checks and the evaluation suiteW5Document-system integration, first drafted sections and correctionsW6Your writers work from live sections, then Agent Care handover
Reading the bandBars are drawn from the work, not from a phase plan. No section is drafted before week 3; text cannot be bound to outputs that nobody has finished mapping.
At the end of W6A section of a live report has been drafted, checked against its outputs and rewritten where your writer disagreed. From week 7 the source checks and the version comparison are Agent Care's problem rather than your writer's.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Biotechnology AI agent
Build a writing copilot around the study you have just locked.
Show us one report section, the outputs it is written from and how a draft reaches your medical writer and your statistician today. A copilot that writes well and sources badly is worse than no copilot, so the first three weeks go on the map from text to table, listing and figure, at the dataset version each was read at.
