> ## Documentation Index
> Fetch the complete documentation index at: https://playbook.pharmatools.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Home

> Use AI to accelerate medical writing without losing scientific accuracy or regulatory control.

export const DownloadCounter = () => {
  if (typeof window !== 'undefined' && !window.__pbCounterStarted) {
    window.__pbCounterStarted = true;
    const apply = n => {
      const el = document.getElementById('playbook-downloads');
      if (el) el.textContent = n.toLocaleString();
    };
    const tryFetch = () => {
      fetch('https://playbook-counter.pharmatools.workers.dev/').then(r => r.json()).then(d => {
        if (typeof d.downloads === 'number') {
          apply(d.downloads);
          setTimeout(() => apply(d.downloads), 500);
          setTimeout(() => apply(d.downloads), 1500);
        }
      }).catch(() => {});
    };
    if (document.readyState === 'loading') {
      document.addEventListener('DOMContentLoaded', tryFetch);
    } else {
      tryFetch();
    }
  }
  return null;
};

<div
  className="playbook-hero"
  style={{
width: '100%',
padding: '3.5rem clamp(1.5rem, 5vw, 4rem) 4.5rem',
background: 'linear-gradient(90deg, #0c1442 0%, #234a7d 100%)',
color: '#ffffff',
position: 'relative',
overflow: 'hidden'
}}
>
  <div style={{ maxWidth: '1100px', margin: '0 auto' }}>
    <div
      style={{
  display: 'flex',
  justifyContent: 'space-between',
  fontSize: '0.7rem',
  letterSpacing: '0.12em',
  textTransform: 'uppercase',
  color: '#ffffff',
  marginBottom: '3rem',
  flexWrap: 'wrap',
  gap: '0.5rem'
}}
    >
      <span>A free resource by PharmaTools.AI</span>
      <span>v2.4</span>
    </div>

    <h1
      style={{
  fontSize: 'clamp(2.5rem, 6vw, 4.75rem)',
  fontWeight: 800,
  lineHeight: 1,
  margin: '0 0 2rem',
  color: '#ffffff',
  letterSpacing: '-0.02em'
}}
    >
      <span style={{ display: 'block', lineHeight: 1 }}>Medical Writing</span>
      <span style={{
                display: 'block',
                lineHeight: 1,
                marginTop: '-0.05em',
                paddingBottom: '0.15em',
                background: 'linear-gradient(90deg, #60a5fa 0%, #a78bfa 100%)',
                WebkitBackgroundClip: 'text',
                WebkitTextFillColor: 'transparent',
                backgroundClip: 'text'
              }}>AI Playbook.</span>
    </h1>

    <p
      style={{
  fontSize: 'clamp(1rem, 1.4vw, 1.2rem)',
  lineHeight: 1.55,
  maxWidth: '44rem',
  color: 'rgba(255,255,255,0.85)',
  margin: '0 0 2.25rem'
}}
    >
      Use AI across the full writing lifecycle – <strong style={{ color: 'inherit', fontWeight: 700 }}>finding evidence, drafting, checking claims, preparing for review</strong> – without losing scientific accuracy or regulatory control.
    </p>

    <div style={{ display: 'flex', gap: '0.75rem', flexWrap: 'wrap' }}>
      <a href="/start" style={{
                display: 'inline-block',
                padding: '0.85rem 1.6rem',
                background: '#ffffff',
                color: '#0b0f2c',
                borderRadius: '0.6rem',
                fontWeight: 600,
                textDecoration: 'none',
                fontSize: '0.95rem'
              }}>Start here →</a>
      <a href="#what-do-you-need-to-do" style={{
                display: 'inline-block',
                padding: '0.85rem 1.6rem',
                background: 'transparent',
                color: '#ffffff',
                border: '1px solid rgba(255,255,255,0.25)',
                borderRadius: '0.6rem',
                fontWeight: 600,
                textDecoration: 'none',
                fontSize: '0.95rem'
              }}>Browse 18 workflows</a>
      <a href="https://playbook-counter.pharmatools.workers.dev/download" style={{
                display: 'inline-block',
                padding: '0.85rem 1.6rem',
                background: 'transparent',
                color: '#ffffff',
                border: '1px solid rgba(255,255,255,0.25)',
                borderRadius: '0.6rem',
                fontWeight: 600,
                textDecoration: 'none',
                fontSize: '0.95rem'
              }}>Download as PDF ↓</a>
    </div>

    <p
      style={{
  marginTop: '0.85rem',
  fontSize: '0.8rem',
  color: 'rgba(255,255,255,0.55)',
  margin: '0.85rem 0 0',
  letterSpacing: '0.01em'
}}
    >
      <span id="playbook-downloads">—</span> downloads so far
    </p>

    <p
      style={{
  marginTop: '1.5rem',
  fontSize: '0.9rem',
  color: 'rgba(255,255,255,0.7)',
  margin: '1.5rem 0 0'
}}
    >
      A growing resource for healthcare communications teams adopting AI workflows.
    </p>
  </div>
</div>

<DownloadCounter />

Each workflow explains:

* what AI can help with
* what the writer must verify
* where mistakes commonly happen

**AI for acceleration, not authority. Translation, not invention.**

***

## What's new

<Update label="Latest updates" description="Recent additions to the playbook">
  * **v2.4** — The full playbook is now available as a [downloadable PDF](https://github.com/nickjlamb/medical-writing-ai-playbook/releases/latest/download/playbook.pdf) — every page in a single A4 file, auto-rebuilt on every content update
  * **v2.23** — New [Generate Concept Visuals](/workflows/generate-concept-visuals) workflow covering AI image generation (Nano Banana 2, Midjourney) with prompting patterns and a reality check on what AI images must not be used for
  * **v2.22** — [Claude Design](/tools/ecosystem#claude-design) added to the Tool ecosystem under a new **Design and brand concepting** section, framed for medical writers taking on earlier-stage visual concepting

  [See the full changelog →](/changelog)
</Update>

***

## The workflow lifecycle

<Frame>
  <img src="https://mintcdn.com/pharmatoolsai/sBjwu_mmX8U6AbVW/lifecycle.svg?fit=max&auto=format&n=sBjwu_mmX8U6AbVW&q=85&s=2d96e96319f13b66e9bb9d0126a87779" alt="The medical writing AI workflow lifecycle: Evidence, Insight, Draft, Adapt, Validate, Deliver" width="1200" height="540" data-path="lifecycle.svg" />
</Frame>

| Stage        | Workflows                                                                                                                                                                                                                                                                                                                                                             |
| ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Evidence** | [Find Evidence](/workflows/find-evidence) · [Summarise a Paper](/workflows/summarise-source-paper) · [Congress Summary](/workflows/prepare-congress-or-poster-summary)                                                                                                                                                                                                |
| **Insight**  | [Extract Study Data](/workflows/extract-study-data) · [Extract Key Messages](/workflows/extract-key-messages)                                                                                                                                                                                                                                                         |
| **Draft**    | [Build an Outline](/workflows/build-content-outline) · [Write a Manuscript](/workflows/write-a-manuscript) · [Regulatory Document](/workflows/draft-regulatory-document) · [Convert Stats to Narrative](/workflows/convert-stats-to-narrative) · [Create a Slide Deck](/workflows/create-medical-slide-deck) · [Concept Visuals](/workflows/generate-concept-visuals) |
| **Adapt**    | [Adapt for Audiences](/workflows/adapt-for-different-audiences) · [Plain Language Summary](/workflows/create-plain-language-summary)                                                                                                                                                                                                                                  |
| **Validate** | [Verify Claims](/workflows/verify-claims-against-references) · [Compliance Check](/workflows/check-promotional-compliance) · [Check Document Consistency](/workflows/check-document-consistency)                                                                                                                                                                      |
| **Deliver**  | [Repurpose Content](/workflows/repurpose-content-across-channels) · [Final Review](/workflows/final-human-review)                                                                                                                                                                                                                                                     |

<div
  style={{
margin: '2.5rem 0 0',
padding: '1.25rem 1.5rem',
borderLeft: '3px solid rgba(99, 102, 241, 0.35)',
background: 'rgba(99, 102, 241, 0.04)',
borderRadius: '0 0.4rem 0.4rem 0'
}}
>
  <p style={{
    fontSize: '0.7rem',
    letterSpacing: '0.12em',
    textTransform: 'uppercase',
    fontWeight: 600,
    margin: '0 0 0.6rem',
    color: 'rgba(99, 102, 241, 0.9)'
  }}>Most explored workflows</p>

  <ul style={{ margin: 0, paddingLeft: '1.1rem', fontSize: '0.95rem', lineHeight: 1.7 }}>
    <li><a href="/workflows/find-evidence">Finding evidence</a></li>
    <li><a href="/workflows/verify-claims-against-references">Verifying claims against references</a></li>
    <li><a href="/workflows/summarise-source-paper">Summarising source papers</a></li>
    <li><a href="/workflows/create-plain-language-summary">Creating plain language summaries</a></li>
  </ul>
</div>

***

## What do you need to do?

<CardGroup cols={3}>
  <Card title="Find evidence" icon="microscope" href="/workflows/find-evidence">
    Search biomedical databases and build a curated evidence set.
  </Card>

  <Card title="Summarise a paper" icon="file-text" href="/workflows/summarise-source-paper">
    Structured summary from a published paper or congress poster.
  </Card>

  <Card title="Congress coverage" icon="presentation" href="/workflows/prepare-congress-or-poster-summary">
    Structured poster extractions for rapid congress turnaround.
  </Card>
</CardGroup>

<CardGroup cols={2}>
  <Card title="Extract study data" icon="file-text" href="/workflows/extract-study-data">
    Pull endpoints, outcomes, and study details into evidence tables.
  </Card>

  <Card title="Extract key messages" icon="key" href="/workflows/extract-key-messages">
    Evidence-supported messages from clinical data, organised by theme.
  </Card>
</CardGroup>

<CardGroup cols={3}>
  <Card title="Build an outline" icon="list-check" href="/workflows/build-content-outline">
    Structure a deliverable from key messages and source materials.
  </Card>

  <Card title="Write a manuscript" icon="pen-line" href="/workflows/write-a-manuscript">
    Draft a scientific manuscript from study data and references.
  </Card>

  <Card title="Regulatory document" icon="file-text" href="/workflows/draft-regulatory-document">
    Draft CSR sections, IBs, or Module 2 summaries from source data.
  </Card>
</CardGroup>

<CardGroup cols={3}>
  <Card title="Stats to narrative" icon="file-text" href="/workflows/convert-stats-to-narrative">
    Convert statistical outputs and tables into neutral regulatory prose.
  </Card>

  <Card title="Create a slide deck" icon="presentation" href="/workflows/create-medical-slide-deck">
    Slides for MSL training, advisory boards, or medical education.
  </Card>

  <Card title="Concept visuals" icon="image" href="/workflows/generate-concept-visuals">
    AI image generation for concept figures, visual abstracts, and social graphics.
  </Card>
</CardGroup>

<CardGroup cols={2}>
  <Card title="Adapt for audiences" icon="users" href="/workflows/adapt-for-different-audiences">
    Specialist content rewritten for GPs, nurses, payers, or patients.
  </Card>

  <Card title="Plain language summary" icon="heart-pulse" href="/workflows/create-plain-language-summary">
    Clinical findings translated into language patients can understand.
  </Card>
</CardGroup>

<CardGroup cols={3}>
  <Card title="Verify claims" icon="search" href="/workflows/verify-claims-against-references">
    Systematic claim-to-reference checking before formal review.
  </Card>

  <Card title="Compliance check" icon="shield" href="/workflows/check-promotional-compliance">
    Pre-screen for compliance signals before MLR submission.
  </Card>

  <Card title="Document consistency" icon="search" href="/workflows/check-document-consistency">
    Flag inconsistencies in values, terms, and cross-references.
  </Card>
</CardGroup>

<CardGroup cols={2}>
  <Card title="Repurpose content" icon="repeat" href="/workflows/repurpose-content-across-channels">
    Approved content adapted across channels and formats.
  </Card>

  <Card title="Final review" icon="clipboard-check" href="/workflows/final-human-review">
    The QC gate before any AI-assisted deliverable ships.
  </Card>
</CardGroup>

***

## 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.

<CardGroup cols={3}>
  <Card title="Human-in-the-loop" icon="user-check" href="/principles/human-in-the-loop">
    AI drafts. A named professional verifies and signs off. No exceptions.
  </Card>

  <Card title="Source grounding" icon="book-open" href="/principles/source-grounding">
    Every claim traces to a cited source. Nothing enters from AI training data.
  </Card>

  <Card title="Risk tiers" icon="gauge" href="/principles/risk-levels">
    Four levels define what AI can contribute and what review intensity is required.
  </Card>

  <Card title="Review accountability" icon="clipboard-check" href="/principles/review-and-accountability">
    Sign-off protocols, audit trails, and clear ownership for every deliverable.
  </Card>

  <Card title="Declaring AI use" icon="file-pen" href="/principles/declaring-ai-use">
    What to disclose to journals, regulators, and clients when AI is part of the work.
  </Card>

  <Card title="AI regulation in pharma" icon="scale-balanced" href="/principles/ai-regulation">
    The EU AI Act, FDA, EMA, MHRA — and what counts as high-risk in medical writing.
  </Card>

  <Card title="Choosing your model" icon="compass" href="/principles/choosing-your-model">
    When to reach for a reasoning model and when a standard LLM is enough.
  </Card>

  <Card title="Agentic workflows" icon="circle-nodes" href="/principles/agentic-workflows">
    When an agent earns its keep — and when it doesn't.
  </Card>

  <Card title="AI in peer review" icon="magnifying-glass" href="/principles/ai-in-peer-review">
    What journals run on your manuscript before a human reviewer sees it.
  </Card>
</CardGroup>

***

## 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        |

<Card title="Full risk framework →" icon="shield-check" href="/principles/ai-risk-framework">
  Workflow-by-workflow risk tiers and review expectations
</Card>

***

## Tools

Purpose-built tools from [PharmaTools.AI](https://pharmatools.ai) for the workflow steps where general-purpose LLMs fall short.

<CardGroup cols={3}>
  <Card title="PubCrawl" icon="microscope" href="/tools/pubcrawl">
    Literature search and evidence discovery.
  </Card>

  <Card title="RefCheckr" icon="search" href="/tools/refcheckr">
    Closed-loop claim verification and rewrite.
  </Card>

  <Card title="MedCheckr" icon="shield" href="/tools/medcheckr">
    Promotional compliance screening.
  </Card>

  <Card title="Patiently AI" icon="heart" href="/tools/patiently-ai">
    Clinical-to-patient language translation.
  </Card>

  <Card title="LLMentor" icon="users" href="/tools/llmentor">
    Multi-audience content adaptation.
  </Card>

  <Card title="PLS Generator" icon="file-text" href="/tools/pls-generator">
    Plain language summaries from clinical data.
  </Card>

  <Card title="PosterLens" icon="image" href="/tools/posterlens">
    Structured extraction from scientific posters.
  </Card>
</CardGroup>

***

<Card title="New here? Start with the guided reading order →" icon="arrow-right" href="/start">
  Role-specific recommendations for medical writers, agency teams, and pharma stakeholders.
</Card>

*A free resource from [PharmaTools.AI](https://pharmatools.ai) · v2.3*