Skip to main content
The playbook covers different workflows at different risk levels. The best starting point depends on what you do.

​
For freelance or in-house medical writers

Read first:
  1. Risk Levels — which of your deliverables fall into which tier
  2. Human-in-the-Loop — the review framework for every AI-assisted output
Start with these workflows:
  1. Summarise a Source Paper — low risk, mirrors work you already do
  2. Extract Key Messages — medium risk, saves time in early-stage content development
  3. Build a Content Outline — low risk, works for any deliverable type
Before anything leaves your desk:Most relevant tools:
  • RefCheckr — claim verification in multi-reference documents
  • PosterLens — rapid congress poster extraction
What this gives you: A documented process you can stand behind. When a client asks how you used AI, you can point to the workflow you followed, the review steps you completed, and the checklist you used — not just “I used AI to help draft this.”
Regardless of role, this is a practical path through the playbook:
1

Understand the foundation

Read Human-in-the-Loop and Source Grounding.
2

Learn the risk framework

Read Risk Levels — which tasks carry which level of risk.
3

Try a low-risk workflow

Start with Summarise a Source Paper. It demonstrates the full workflow card structure.
4

Build up to higher-risk workflows

Work through Extract Key Messages and Adapt for Audiences.
5

Always finish with review

Run every AI-assisted deliverable through Final Human Review.