# Medical Writing AI Playbook

## Docs

- [About the Author](https://playbook.pharmatools.ai/about.md): Why this playbook exists, and the background behind it.
- [Changelog](https://playbook.pharmatools.ai/changelog.md): Version history and updates to the Medical Writing AI Playbook.
- [Glossary](https://playbook.pharmatools.ai/glossary.md): Definitions for abbreviations and terms used across the Medical Writing AI Playbook.
- [Home](https://playbook.pharmatools.ai/index.md): Use AI to accelerate medical writing without losing scientific accuracy or regulatory control.
- [Agentic Workflows](https://playbook.pharmatools.ai/principles/agentic-workflows.md): When an AI agent earns its keep, when it doesn't, and how to assess agentic workflows for medical writing — with RefCheckr as the worked example.
- [AI Failure Modes in Medical Writing](https://playbook.pharmatools.ai/principles/ai-failure-modes.md): Common ways AI can go wrong when working with scientific evidence, and how to catch them.
- [AI in Peer Review](https://playbook.pharmatools.ai/principles/ai-in-peer-review.md): What journals run on your manuscript before a human reviewer sees it — and what that means for pre-submission QC.
- [AI Regulation in Pharma](https://playbook.pharmatools.ai/principles/ai-regulation.md): How the EU AI Act and other regulatory frameworks shape AI use in medical writing — what counts as high-risk, what doesn't, and how to assess your tools.
- [AI Risk Framework for Medical Writing](https://playbook.pharmatools.ai/principles/ai-risk-framework.md): A practical framework for deciding where AI can assist, where it needs stricter review, and where human authority must remain primary.
- [Choosing Your Model](https://playbook.pharmatools.ai/principles/choosing-your-model.md): When to reach for a reasoning model, when a standard LLM is enough, and how to match model choice to the task in front of you.
- [Declaring AI Use](https://playbook.pharmatools.ai/principles/declaring-ai-use.md): What journals, regulators, and clients expect you to disclose when AI is part of the writing process, and what 'use' actually means.
- [Human-in-the-Loop Decision Making](https://playbook.pharmatools.ai/principles/human-in-the-loop.md): Every deliverable has a named owner. AI produces working material; a qualified professional verifies, edits, and signs off.
- [Review and Accountability](https://playbook.pharmatools.ai/principles/review-and-accountability.md): Structured sign-off protocols, audit trails, and documentation requirements for AI-assisted deliverables.
- [Understanding AI Risk in Medical Writing](https://playbook.pharmatools.ai/principles/risk-levels.md): Why AI risk varies across medical writing tasks — failure modes, risk factors, and why some tasks demand more human oversight than others.
- [Source Grounding](https://playbook.pharmatools.ai/principles/source-grounding.md): Every claim traces to a specific source document. No content enters a deliverable from AI training data.
- [Adaptation Prompts](https://playbook.pharmatools.ai/prompts/adaptation-prompts.md): Prompt patterns for adapting medical content across audience levels, channels, and formats.
- [Outlining Prompts](https://playbook.pharmatools.ai/prompts/outlining-prompts.md): Prompt patterns for building content outlines and structures for medical communications deliverables.
- [Review Prompts](https://playbook.pharmatools.ai/prompts/review-prompts.md): Prompt patterns for QC, verification, and pre-submission review of medical communications content.
- [Source Analysis Prompts](https://playbook.pharmatools.ai/prompts/source-analysis-prompts.md): Prompt patterns for extracting, structuring, and summarising clinical and scientific source materials.
- [Start Here](https://playbook.pharmatools.ai/start.md): Where to begin based on your role — recommended reading order and starting workflows for medical writers, agencies, and pharma teams.
- [AI Audit-Trail Log Template](https://playbook.pharmatools.ai/templates/ai-audit-trail-log.md): Contemporaneous log of AI use across a project — supports disclosure, sponsor audits, and EU AI Act documentation.
- [Disclosure Language Template](https://playbook.pharmatools.ai/templates/disclosure-language.md): Ready-to-use AI disclosure wording for manuscripts, posters, regulatory documents, and other medical writing deliverables.
- [MLR-with-AI Review Checklist](https://playbook.pharmatools.ai/templates/mlr-ai-review-checklist.md): Structured MLR review checklist with AI-specific checks for promotional and scientific content where AI was used in drafting, editing, or verification.
- [Pre-submission QC Checklist](https://playbook.pharmatools.ai/templates/pre-submission-qc-checklist.md): Final-gate quality control for AI-assisted manuscripts, abstracts, and regulatory submissions — covers the same checks publishers run on receipt.
- [Which tool when](https://playbook.pharmatools.ai/tools/decision-tree.md): A decision guide for choosing the right AI tool for a medical writing task.
- [Tool ecosystem](https://playbook.pharmatools.ai/tools/ecosystem.md): Third-party tools referenced throughout the playbook, organised by the job they help you do.
- [LLMentor](https://playbook.pharmatools.ai/tools/llmentor.md): Adapt medical and scientific content across audience levels while preserving accuracy.
- [MedCheckr](https://playbook.pharmatools.ai/tools/medcheckr.md): Pre-screen medical communications content for promotional compliance signals.
- [Patiently AI](https://playbook.pharmatools.ai/tools/patiently-ai.md): Translate clinical content into patient-friendly language for accessible medical communications.
- [PLS Generator](https://playbook.pharmatools.ai/tools/pls-generator.md): Generate plain language summaries from clinical and scientific source materials.
- [PosterLens](https://playbook.pharmatools.ai/tools/posterlens.md): Extract structured data from scientific posters for congress coverage and summarisation.
- [PubCrawl](https://playbook.pharmatools.ai/tools/pubcrawl.md): Search and explore published literature, clinical trials, and prescribing information to find the evidence that informs your medical writing.
- [RefCheckr](https://playbook.pharmatools.ai/tools/refcheckr.md): Closed-loop AI that verifies, rewrites, and re-checks claims against the source paper.
- [Adapt Content for Different Audiences](https://playbook.pharmatools.ai/workflows/adapt-for-different-audiences.md): Transform reviewed medical content from one audience level to another while preserving factual accuracy.
- [Build a First Content Outline](https://playbook.pharmatools.ai/workflows/build-content-outline.md): Organise key messages and source materials into a structured content outline ready for draft development.
- [Check Document Consistency](https://playbook.pharmatools.ai/workflows/check-document-consistency.md): Use AI to flag inconsistencies in patient numbers, endpoint wording, terminology, and cross-references across long documents.
- [Check Promotional Compliance](https://playbook.pharmatools.ai/workflows/check-promotional-compliance.md): Pre-screen content for promotional compliance signals before formal MLR review.
- [Convert Statistical Outputs to Narrative](https://playbook.pharmatools.ai/workflows/convert-stats-to-narrative.md): Turn tables, figures, and statistical outputs into neutral, regulatory-style prose with exact value preservation.
- [Create a Medical Slide Deck](https://playbook.pharmatools.ai/workflows/create-medical-slide-deck.md): Structure and draft slide-based content for MSL training, advisory boards, congress updates, or medical education.
- [Create a Plain Language Summary](https://playbook.pharmatools.ai/workflows/create-plain-language-summary.md): Draft accessible patient-facing summaries from clinical study reports and published research.
- [Draft a Regulatory Document](https://playbook.pharmatools.ai/workflows/draft-regulatory-document.md): Structure and draft regulatory documents from source materials, with AI support for organisation, summarisation, and first-pass text.
- [Extract Key Messages from Evidence](https://playbook.pharmatools.ai/workflows/extract-key-messages.md): Pull evidence-supported key messages from clinical sources, structured for content development and stakeholder communications.
- [Extract Study Data](https://playbook.pharmatools.ai/workflows/extract-study-data.md): Pull endpoints, outcomes, and study details from clinical papers into structured evidence tables or data summaries.
- [Final Human Review Before Use](https://playbook.pharmatools.ai/workflows/final-human-review.md): Structured final review process for AI-assisted deliverables before submission or publication.
- [Find Evidence](https://playbook.pharmatools.ai/workflows/find-evidence.md): Search biomedical databases, screen results, and build an evidence set to support a medical writing project.
- [Generate Concept Visuals with AI](https://playbook.pharmatools.ai/workflows/generate-concept-visuals.md): Use AI image generation for conceptual figures, visual abstracts, slide visuals, and social graphics — with the guardrails medical content requires.
- [Prepare a Congress or Poster Summary](https://playbook.pharmatools.ai/workflows/prepare-congress-or-poster-summary.md): Create structured summaries from scientific posters and congress presentations.
- [Repurpose Content Across Channels](https://playbook.pharmatools.ai/workflows/repurpose-content-across-channels.md): Adapt approved content from one format or channel to another while maintaining accuracy and references.
- [Summarise a Source Paper](https://playbook.pharmatools.ai/workflows/summarise-source-paper.md): Turn a published clinical paper into a structured, verified summary ready for downstream medical writing.
- [Verify Claims Against References](https://playbook.pharmatools.ai/workflows/verify-claims-against-references.md): Systematically check whether document claims are accurately supported by their cited references.
- [Write a Manuscript](https://playbook.pharmatools.ai/workflows/write-a-manuscript.md): Draft a scientific manuscript from study data and references, with AI support for structure, section drafting, and synthesis.