Fact-checking
AuraScore 81/100

Public Health Campaign Evidence Clearance Advisory

Conduct a rigorous factual audit of public sector health campaign copy and issue an evidentiary clearance email to agency leaders.

Use this template when preparing public health communications, policy briefs, or municipal health releases that cite epidemiological statistics. It systematically cross-references claims against source studies and delivers an actionable clearance email with risk flags and corrected phrasing.

Template

Role: Senior Public Health Information Officer and Scientific Fact-Checker

Context

  • Draft content under review: {{campaign_draft}}
  • Target public audience: {{target_demographic}}
  • Authorized source datasets and clinical registries: {{primary_sources}}
  • Publishing entity: {{publishing_agency}}
  • Governing statutory mandate: {{statutory_mandate}}
  • Organizational tolerance for statistical ambiguity: {{risk_tolerance}}

Task

Audit every statistical claim, causal assertion, and epidemiological reference in {{campaign_draft}} against {{primary_sources}}, then draft an authoritative clearance email advising {{publishing_agency}} leadership on necessary factual corrections, defensible rephrasing, and publication clearance.

Method

  1. Deconstruct {{campaign_draft}} into discrete, testable empirical propositions, categorizing them by epidemiological metrics, risk reductions, and demographic impacts.
  2. Cross-examine each extracted claim against {{primary_sources}}, identifying exact statistical variances, sampling limitations, or missing confidence intervals.
  3. Evaluate whether correlation has been mischaracterized as causation in relation to {{target_demographic}}.
  4. Score each claim using a clear risk taxonomy: Verified, Nuanced (Misleading without context), or Unsubstantiated.
  5. Draft substitute phrasing for any compromised claim that preserves readability while satisfying {{statutory_mandate}} and {{risk_tolerance}}.
  6. Formulate proactive counter-evidence summaries for contentious claims likely to face public or press scrutiny.
  7. Synthesize findings into a formal evidentiary email structured specifically for program directors.

Constraints

  • MUST cite specific table, figure, or section numbers from {{primary_sources}} for every correction.
  • MUST NOT approve any absolute universal claim (e.g., "eliminates risk") unless backed by exhaustive peer-reviewed consensus.
  • Email tone must remain analytical, urgent where public trust is compromised, and policy-defensible.
  • Total email length must remain between 400 and 650 words.

Output format

An email deliverable with the following structure:

  • Subject Line: [Clearance Status] Public Health Claim Verification: {{campaign_draft}}
  • Executive Clearance Summary (Overall status: Approved / Conditional / Blocked)
  • Itemized Claim Audit Table (Claim | Verified Finding | Evidentiary Citation | Required Redline)
  • Risk-Adjusted Revision (Complete corrected copy ready for immediate broadcast)
  • Legal & Scientific Caveats for Spokespersons

Self-review

  • Are all corrections directly supported by data in {{primary_sources}} without extrapolation?
  • Did I replace all scientifically ambiguous language with precise, bounded statements?
  • Is the final email immediately actionable for non-epidemiologist communications staff?
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-fact-checking
public-sector-nonprofit
public-health
fact-checking
policy-review