- what AI can help with
- what the writer must verify
- where mistakes commonly happen
What’s new
Recent additions to the playbook
- v2.8 — Choosing Your Model now covers the energy and water behind AI use, and why picking a bigger model than the job needs wastes both. Check your own with the AI Water and Energy Footprint Calculator. Agentic Workflows has a matching note on when a multi-step AI process isn’t worth the extra cost
- v2.7 — AI Regulation in Pharma updated now the EU AI Act’s transparency rules are in force (2 August 2026). AI companies have started marking their own output: Claude and Gemini add an invisible watermark to text, and AI-generated images carry hidden labels. Marking is their job, not yours — and it doesn’t replace declaring that you used AI
- v2.6 — Declaring AI Use and the disclosure templates updated for JAMA’s stricter policy (August 2026). Three things are now banned outright rather than simply declared: letting AI generate or format references, using AI to draft Opinion pieces and Letters, and AI-made clinical images
The workflow lifecycle
Most explored workflows
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.
Concept visuals
AI image generation for concept figures, visual abstracts, and social graphics.
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
The principles that shape every workflow in this playbook — what counts as appropriate AI use, how to verify it, what to disclose, and where the regulatory limits sit.Human-in-the-loop
AI drafts. A named professional verifies and signs off. No exceptions.
Source grounding
Every claim traces to a cited source. Nothing enters from AI training data.
Description & Discernment
Brief with rich context, evaluate for voice and accuracy, refine with specifics.
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.
Declaring AI use
What to disclose to journals, regulators, and clients when AI is part of the work.
AI regulation in pharma
The EU AI Act, FDA, EMA, MHRA — and what counts as high-risk in medical writing.
Choosing your model
When to reach for a reasoning model and when a standard LLM is enough.
Agentic workflows
When an agent earns its keep — and when it doesn’t.
AI in peer review
What journals run on your manuscript before a human reviewer sees it.
Risk tiers
Not all tasks carry the same consequences. Four tiers define the AI role, the review process, and what sign-off is required.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
Closed-loop claim verification and rewrite.
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.