Skip to main content
Take reviewed content written for one audience and produce a version for another — adjusting language, complexity, emphasis, and framing while preserving every factual claim. This workflow transforms existing content; it does not create new content.
Risk tier: Medium (higher when adapting for patients or regulatory-sensitive contexts)  ·  Review requirement: Enhanced review with source cross-checkOnly adapt content that has already been reviewed for accuracy. Adapting unverified content propagates any errors it contains into every audience version.

​
What AI does

  • Rapidly adjusts language complexity and terminology for different professional or lay audiences
  • Restructures content emphasis to match audience priorities (e.g., shifting from efficacy-led to practical-considerations-led for nurses)
  • Produces multiple audience versions from a single source for comparison
  • Suggests alternative phrasings for complex medical concepts

​
What AI cannot do

AI adapts everything — it does not decide what the audience actually needs to know, whether a simplification has changed the meaning of a claim, or whether the adapted version meets the compliance requirements for a new context. These are human decisions.

​
Before you start

  • Confirm that your source content has been reviewed and verified for accuracy. Do not adapt unreviewed content.
  • Be specific about your target audience — “HCPs” is not a useful audience specification. “Community pharmacists in primary care” is.
  • Identify whether the adaptation changes the regulatory context (e.g., from HCP to patient, from scientific to promotional). If it does, the compliance requirements change.
The more precisely you specify the target audience in your prompt — their role, knowledge level, priorities, and information needs — the more useful the AI-generated adaptation will be.

​
Steps

1

Start with verified source content

Confirm that the source content is reviewed and accurate before adapting it. This workflow transforms — it does not correct. Errors in the source become errors in every adapted version.
2

Define the target audience precisely

Write a specific audience description: role, setting, knowledge level, and what they need from this content. Generic audience labels produce generic adaptations.
3

Identify regulatory context changes

Determine whether the adaptation changes the compliance context (scientific to promotional, HCP to patient). If it does, plan for the additional compliance review before generating the adaptation.
4

Generate the adapted version

Provide the source content and audience specification to LLMentor or your AI tool using the prompt pattern below.
5

Review for meaning preservation

This is the most critical check. Has the adaptation changed what the content says, not just how it says it? Read every clinical claim in the adapted version and trace it back to the source.
6

Check qualifiers are preserved

List every qualifier in the source — population, subgroup, comparator, analysis type, hedged language — and confirm each is preserved or appropriately rephrased in the adapted version.
7

Verify safety information is complete

Safety information must be present in every adapted version regardless of format constraints. If space is limited, compress — do not remove.
8

Confirm no new claims were introduced

Verify that every statement in the adapted version traces to the source. Background context sentences are the most common source of AI-introduced information.
9

Compliance review

If the adapted version has different regulatory requirements from the original, ensure it meets those requirements before use.

​
Prompt pattern

You are a medical writing assistant specialising in audience adaptation. Your task is to adapt the following content for a different audience.

Source content:
[INSERT REVIEWED SOURCE CONTENT]

Original audience: [SPECIFY — e.g., oncologists, clinical researchers]
Target audience: [SPECIFY — e.g., general practitioners, primary care nurses, patients with moderate health literacy]

Adaptation requirements:
- Adjust language complexity and terminology for the target audience
- Maintain all factual accuracy — do not change what the content says, only how it says it
- Preserve key data points and findings
- Adjust emphasis to reflect the target audience's priorities and information needs
- [SPECIFY any format or length requirements]

Rules:
- Do not add information that is not in the source content
- Do not remove safety information or important limitations
- If a medical term is simplified, ensure the simplified version is medically accurate
- If the source includes specific data (numbers, statistics), retain them unless the adaptation format explicitly calls for a non-data summary
- Flag any areas where simplification may have changed the meaning with [REVIEW]

​
Audience-specific considerations

When adapting across HCP types (e.g., specialist to GP), focus on shifting from mechanistic detail to practical clinical application. Ensure efficacy data is contextualised for the GP’s patient population, not just the trial population.

​
Human review checklist

  • All factual claims in the adapted version match the source content
  • No new information has been introduced that is not in the source
  • Safety information is preserved and appropriately represented
  • Qualifiers and limitations are retained
  • Language is genuinely appropriate for the target audience (not just slightly simplified)
  • Medical terms that have been simplified remain accurate
  • Data points are correctly reproduced
  • The adapted version meets regulatory or compliance requirements for the target audience and channel
  • Emphasis and framing are appropriate for the target audience’s priorities

​
Common failure modes

RiskWhat to look for
Meaning drift”Non-inferior to Treatment Y” becomes “works as well as Treatment Y” — these are not the same claim
Lost qualifiersPopulation restriction (“moderate-to-severe disease”) dropped from the adapted version, making the claim appear to cover all patients
Inappropriate certainty”May provide benefit” or “showed a trend” becomes “provides benefit” or “improved outcomes”
Omitted safety informationSafety section cut to save space in a condensed format
New claims introducedAI adds background context from its training data, not from the source content

​
Relevant tools

LLMentor

Primary tool for audience-level adaptation across professional audiences.

Patiently AI

Specialised tool for adapting content to patient and carer audiences.

​
Next steps

Plain Language Summary

If your target audience is patients or carers, use this specialised workflow.

Repurpose Content

Adapt the output for different channel formats.

Final Review

Verify the adapted version before use.