PlaysbyMoat8
Back to the library
The workflow guideMarketing

Prepare a substantiation packet for regulated marketing claims

Break a marketing draft into reviewable claims, link each claim to supplied scientific and product evidence, and flag unsupported wording for specialist approval.

6 implementation stepsIntermediate

How this works

Use this to prepare a draft for regulated marketing review, with the intended product, audience, jurisdiction and channel explicitly stated. The output connects individual claims to approved product information and scientific evidence. It also identifies the wording that needs a reviewer’s judgment before the asset can progress.

Evidence retrieval is different from approval. A paper mentioning a product category does not substantiate every claim about a particular product, and a statistically significant result does not establish a general marketing promise. Preserve population, endpoint, comparator, limitations and publication context. The assistant pre-screens the draft; specialists own the final interpretation.

Before you start

Defined asset scope

Record product version, audience, market, channel and the planned review stage.

Approved evidence set

Obtain current product information, approved claims, relevant scientific sources and the team’s review rules.

Review ownership

Identify the medical, regulatory and legal reviewers and the status vocabulary they use.

Prepare the inputs

marketing_draft
Required

Text plus asset or slide identifiers

Include captions, charts, footnotes and implied comparative claims.

evidence_library
Required

Approved documents with versions

Keep full source locations and known restrictions; do not substitute search snippets for supporting text.

review_rules
Required

Versioned audience and market rules

The reviewer supplies or verifies applicability; no invented compliance checklist.

approved_claims
Optional / conditional

Optional approved wording register

Check product, market and audience match before reusing approval.

Implementation, step by step

  1. Freeze the review version

    • Assign an asset version and preserve the original wording and layout references.
    • Record the product, audience and market so later edits cannot reuse an approval out of context.

    Checkpoint: The review packet identifies exactly what is being assessed.

  2. Separate explicit and implied claims

    • Extract factual, comparative, numerical and benefit claims into atomic rows.
    • Include chart headlines and image captions; distinguish factual statements from editorial tone.

    Checkpoint: Each claim maps to a precise location in the draft.

  3. Retrieve appropriate support

    • Find supplied product or scientific evidence addressing the same population, endpoint and comparison.
    • Record limitations and whether the support is direct, partial, contradictory or absent.

    Checkpoint: Every support judgment cites a document passage and a match rationale.

  4. Pre-screen wording and context

    • Compare the claim with approved language and the reviewer-supplied rules.
    • Flag overstated certainty, missing qualifications and unsupported extrapolation without pronouncing the asset legally compliant.

    Checkpoint: The matrix identifies the exact wording and reason requiring review.

  5. Prepare a controlled revision

    • Suggest narrower wording only when the evidence supports it and retain the original for comparison.
    • Keep unresolved claims in the marked draft rather than silently removing inconvenient issues.

    Checkpoint: Reviewers receive a traceable change proposal and unresolved-question list.

  6. Reconcile reviewer decisions

    • Record each reviewer’s disposition against the frozen asset version.
    • If the team changes product facts, audience or substantive wording, flag the affected claims for another review.

    Checkpoint: Approval status cannot be transferred to an unreviewed version.

Decisions along the way

A source supports a narrower population or endpoint

Show the mismatch and suggest explicitly qualified wording for specialist review.

No approved evidence supports a claim

Mark unsupported and request support or removal; never fabricate a citation.

What you will produce

claim-substantiation.xlsx

Workbook

Evidence preparation for the approval process.

Include: claim_id · asset_location · claim · source · support_scope · limitation · review_status

marked-marketing-draft.md

Markdown

Proposed edits with unresolved issues intact.

Include: original_wording · proposed_wording · reason · reviewer

Check the result

  • Open every citation and verify it supports the specific statement.
  • Check numeric claims, denominators, qualifiers and comparator wording.
  • Verify the approval scope matches product, audience, market and asset version.
  • Ensure missing evidence is not labeled compliant or low risk by default.

When something goes wrong

Only an abstract or search snippet is available

Label the limited evidence and request the appropriate full source before substantiation.

Evidence documents contradict one another

Retain the conflict and refer it to the medical reviewer instead of averaging conclusions.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Synthetic: prepare a product brochure for review.

Inputs

The draft says all users improve within one week. The supplied study reports a defined endpoint in a limited adult study group, with variation in response.

Expected result

Flag the universal wording, attach the actual study scope and request medical review of a qualified statement. No automatic approval or treatment advice is produced.

Run a small pilot

Start small

Use previously reviewed assets with known overstated claims and missing citations.

Record the baseline

Measure omitted review issues and time spent locating support manually.

Agree success criteria

Agree claim-coverage and false-substantiation thresholds with the review team.

Stop or revise

Stop clearance recommendations if the current product information or applicable review rules are missing.

Keep the scope clear

  • This is an internal preparation workflow, not medical guidance or a regulatory compliance certification.
  • Publishing, sending and final claim approval remain separate authorized actions.

Check before using

Qualified medical, regulatory and legal reviewers decide whether a claim is accurate, applicable and permitted for the intended audience.

Business activities

  • Create and publish content
  • Run advertising and acquisition tests
  • Operate and improve AI workflows

Editorially adapted workflow; not independently tested.

FROM A RECIPE TO YOUR WORKFLOW

Bring the company context together.

This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.

For this recipe: marketing draft · evidence library · review rules · approved claims

Start with one recurring task, agree which sources to use, and review the first result with your team.

Discuss this workflow

What does your team do?

Choose the recurring work you would like to improve.

A field guide, made for work.

Plays is a curated library of anonymized business workflows. Each recipe explains the inputs, steps, tools, and checks you can adapt to your team. These are editorial guides, not independently tested implementations.

When you share a company website, the guide may read a limited number of public pages on that website. Messages and retrieved page text are sent to our AI provider, NVIDIA, to recommend relevant workflows. Share a general description rather than confidential information.

Saved workflows and selected activities stay in this browser. Your chat history and selected company website are kept in this tab and cleared when you reload or start a new chat. The server does not store conversations. Live source monitoring is not enabled.

If you allow analytics, PostHog receives page views and actions such as workflow saves, skill downloads and link clicks. Random browser and session identifiers connect these actions without identifying you by name. Your choice and browser identifier expire after 90 days; sessions restart after 30 minutes of inactivity or 24 hours. We use local storage, not analytics cookies. Messages, company URLs, search text, full referrers and IP addresses are not sent. There are no person profiles or session recordings. You can decline or withdraw in Analytics settings; Do Not Track and Global Privacy Control keep analytics off.

Read the Plays Privacy Notice ↗