Fact-checking
AuraScore 81/100

Packaged Goods Nutritional Claim and Clinical Evidence Verification

Verify on-pack functional health claims against clinical trials and regulatory standards in an email brief.

Use prior to final CPG packaging print runs to cross-examine ingredient efficacy claims against primary scientific literature. It creates an evidentiary fact-checking email outlining approved versus unsubstantiated statements.

Template

Role: Principal Regulatory Affairs Scientist & CPG Evidence Substantiation Specialist.

Context

  • Brand: {{cpg_brand}}
  • Product Formulation: {{formulation_identifier}}
  • Draft Claims on Packaging: {{on_pack_health_claims}}
  • Scientific Dossier: {{clinical_study_citations}}
  • Target Regulatory Framework: {{regulatory_jurisdiction}}
  • Recipient: {{marketing_lead}}

Task

Draft a technical regulatory fact-checking email evaluating proposed on-pack health and functional claims against provided clinical literature to ensure claims do not exceed scientific proof or trigger regulatory enforcement.

Method

  1. Dissect each claim in {{on_pack_health_claims}} into specific biological endpoints (e.g., immunity, gut health, metabolic boost).
  2. Review {{clinical_study_citations}} to confirm whether studied dosages and delivery formats match the active concentrations in {{formulation_identifier}}.
  3. Evaluate clinical study rigor (sample size, peer-review status, human in-vivo vs. animal/in-vitro models) to determine evidentiary robustness.
  4. Check claim wording against {{regulatory_jurisdiction}} standards for structure/function vs. prohibited disease-prevention or medicinal claims.
  5. Highlight 'dose disconnects' where marketing text implies benefits observed only at significantly higher active ingredient concentrations.
  6. Formulate precise qualifying statements (e.g., 'supports healthy...', 'when combined with...') to bring non-compliant copy into scientific alignment.
  7. Synthesize findings into a structured, executive-ready fact-checking email addressed to {{marketing_lead}}.

Constraints

  • MUST explicitly flag any claim that implies disease mitigation, cure, or treatment under {{regulatory_jurisdiction}} rules.
  • MUST NOT validate any statement whose supporting study used a different delivery vehicle or sub-therapeutic concentration.
  • Every non-compliant claim must be paired with an approved, scientifically verified alternative.
  • Maintain an authoritative, rigorous scientific and compliance tone.

Output format

An email to {{marketing_lead}} organized with:

  • Subject: Regulatory Fact-Check: Evidence Substantiation for {{cpg_brand}} ({{formulation_identifier}})
  • Executive Summary: Brief synopsis (3-4 sentences) on packaging risk level and overall evidentiary strength
  • Claims & Evidence Audit Table: Columns for [On-Pack Claim, Active Ingredient & Dose, Scientific Evidence Level, Compliance Status]
  • Dose Disconnects & Scientific Gaps: Bulleted breakdown of where literature fails to support specific claims
  • Approved Label Copy Alternatives: Side-by-side comparison of original claim vs. substantiated alternative
  • Length constraint: 500-750 words.

Self-review

  1. Did I check active ingredient dosages in {{formulation_identifier}} directly against the quantities cited in {{clinical_study_citations}}?
  2. Are all suggested claim edits compliant with the specific rules of {{regulatory_jurisdiction}}?
  3. Is the distinction between structure/function claims and implied drug claims clearly established?
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
retail-consumer-goods
cpg
fact-checking
regulatory