- what AI can help with
- what the writer must verify
- where mistakes commonly happen
What’s new
- v2.21 — New AI Failure Modes page in Principles: ten predictable ways AI can fail in evidence-based writing, each with example, impact, and how to catch it
- v2.20 — New Which tool when decision guide mapping common medical writing tasks to the right tool
- v2.19 — Claude Cowork coverage expanded with an example workflow and prompt
The workflow lifecycle
| Stage | Workflows |
|---|---|
| Evidence | Find Evidence · Summarise a Paper · Congress Summary |
| Insight | Extract Study Data · Extract Key Messages |
| Draft | Build an Outline · Write a Manuscript · Regulatory Document · Convert Stats to Narrative · Create a Slide Deck |
| Adapt | Adapt for Audiences · Plain Language Summary |
| Validate | Verify Claims · Compliance Check · Check Document Consistency |
| Deliver | Repurpose Content · Final Review |
What do you need to do?
Find evidence
Search biomedical databases and build a curated evidence set.
Summarise a paper
Structured summary from a published paper or congress poster.
Congress coverage
Structured poster extractions for rapid congress turnaround.
Extract study data
Pull endpoints, outcomes, and study details into evidence tables.
Extract key messages
Evidence-supported messages from clinical data, organised by theme.
Build an outline
Structure a deliverable from key messages and source materials.
Write a manuscript
Draft a scientific manuscript from study data and references.
Regulatory document
Draft CSR sections, IBs, or Module 2 summaries from source data.
Stats to narrative
Convert statistical outputs and tables into neutral regulatory prose.
Create a slide deck
Slides for MSL training, advisory boards, or medical education.
Adapt for audiences
Specialist content rewritten for GPs, nurses, payers, or patients.
Plain language summary
Clinical findings translated into language patients can understand.
Verify claims
Systematic claim-to-reference checking before formal review.
Compliance check
Pre-screen for compliance signals before MLR submission.
Document consistency
Flag inconsistencies in values, terms, and cross-references.
Repurpose content
Approved content adapted across channels and formats.
Final review
The QC gate before any AI-assisted deliverable ships.
Principles
Every workflow in this playbook follows four rules. They are not aspirational. They define what review is required before anything leaves your desk.Human-in-the-loop
AI drafts. A named professional verifies and signs off. No exceptions.
Source grounding
Every claim traces to a cited source document. Nothing enters a deliverable from AI training data.
Risk tiers
Four levels define what AI can contribute and what review intensity is required.
Review accountability
Sign-off protocols, audit trails, and clear ownership for every deliverable.
Risk tiers
Not all tasks carry the same consequences. Four tiers define the AI role, the review process, and what sign-off is required.| Tier | AI role | Review required | Examples |
|---|---|---|---|
| Low | First draft, structuring | Standard review | Paper summaries, outlines, internal briefs |
| Medium | Transformation, adaptation | Enhanced review + source cross-check | Key messages, audience adaptation, repurposing |
| High | Limited drafting support | Expert review, full verification | Promotional claims, PLS, compliance checks |
| Critical | Supporting role only | Full expert review, formal sign-off | Final QC before delivery or publication |
Full risk framework →
Workflow-by-workflow risk tiers and review expectations
Tools
Purpose-built tools from PharmaTools.AI for the workflow steps where general-purpose LLMs fall short.PubCrawl
Literature search and evidence discovery.
RefCheckr
Claim-to-reference verification.
MedCheckr
Promotional compliance screening.
Patiently AI
Clinical-to-patient language translation.
LLMentor
Multi-audience content adaptation.
PLS Generator
Plain language summaries from clinical data.
PosterLens
Structured extraction from scientific posters.
New here? Start with the guided reading order →
Role-specific recommendations for medical writers, agency teams, and pharma stakeholders.