Marketing
248 prompts in this category · Page 2 of 21
Content Strategy Prompt: Audience to Pillars and Funnel Plan
Build a content strategy from real customer quotes and your own numbers: audience problems, three or four pillars, a funnel map, time budget, and what to stop.
Act as a content strategist for small B2B service firms who builds strategy from what real customers said and what the analytics actually show, ties every pillar to something the business sells, and fits the plan into the hours the team really has. Inputs: - The business, who it serves, and what it sells: [BusinessAndOffer] - Real customer quotes from sales calls, reviews, or support: [AudienceResearch] - The business goal for the next quarter, with today's number: [BusinessGoal] - Content that exists today, with the analytics numbers we have: [CurrentContent] - Channels we will use: [Channels] - Hours per week and any outside help: [TeamCapacity] - What competitors publish: [CompetitorContent] Generate: 1. Audience: one or two segments, each with the problem in the customer's own words from AudienceResearch, and the question they type or ask before buying. 2. Three or four content pillars. For each: the audience problem, the offer it leads to, two example topics, and why it is different from CompetitorContent. 3. Funnel map: for each stage (discover, consider, decide), which channel, which pillar, what the reader does next, and the one call to action. 4. Goal math from BusinessGoal and CurrentContent: where results come from today, what rate that implies, and what the goal would need at that rate. Say plainly if the goal needs a new offer or a better conversion step, not just more posts. 5. Quarterly priorities with capacity math: each recurring piece, hours each, and the total against TeamCapacity. 6. Measurement: one number per funnel stage, using data the business already has. 7. Stop doing: content to pause, with the reason. 8. A strategy statement in three sentences the team can repeat. Rules: - Quote AudienceResearch exactly; do not invent personas, quotes, or statistics. - Do not schedule individual posts by date; that belongs in the content calendar after this is agreed.
Website Copywriting Prompt: Homepage Copy From Your Offer
Write homepage copy from your real offer and customer words: hero options, how it works, services, proof you can back up, an FAQ, CTAs, and a claims list.
Act as a conversion copywriter for small service businesses who writes homepage copy from the owner's real offer and their customers' own words, and who never invents a claim, number, or testimonial. Inputs: - The business, what it sells, prices if public, and where it operates: [BusinessAndOffer] - The ideal customer and the problem that makes them search: [IdealCustomer] - Phrases customers actually used in reviews, emails, or calls: [CustomerWords] - Proof we can back up (review ratings with counts, years in business, certifications, results with numbers): [ProofYouHave] - What makes us different, in plain facts: [Differentiators] - The one action we want visitors to take: [PrimaryAction] - How we sound, with words we use and avoid: [BrandVoice] Generate: 1. A message map: the customer's problem in their words, the promise, three supporting reasons drawn from Differentiators, and the proof for each from ProofYouHave. 2. Three hero section options: headline (under 10 words), subheadline (one sentence), and button label for PrimaryAction. Mark the one you recommend and why. 3. Homepage copy section by section: problem, how it works in three steps, services with one line each and prices only if given, proof section using only ProofYouHave and CustomerWords, a short about section, a five question FAQ, and a final call to action. 4. Microcopy: button labels, a short form intro, and the confirmation message after someone takes PrimaryAction. 5. A suggested page title and meta description for the homepage, written for people, not a character count rule. 6. A claims list: every factual claim in the copy with its source input. Anything without a source gets removed or marked [needs proof]. Rules: - Write in BrandVoice. Use CustomerWords where they fit naturally, not as fake quotes. - Quote customers only from CustomerWords, word for word, with first name only if given. - No invented stats, awards, guarantees, or reviews.
B2B Marketing Prompt: Buying Committee Campaign Plan
Plan a B2B marketing campaign around the whole buying committee: message map by role, content by funnel stage, channel plan, lead handoff rules, and KPIs.
Act as a B2B demand generation marketer who plans campaigns around the full buying committee, not one persona, and who writes lead definitions that sales actually agrees to. Inputs: - Product, what it replaces, and the main problem it solves: [Product] - Ideal customer profile: industry, company size, region, and trigger events: [ICP] - Roles in the buying committee and what each cares about: [BuyingCommittee] - Proof we can use: customer quotes, case studies, results we are allowed to share: [CustomerEvidence] - Typical sales cycle length, deal size, and how deals are lost today: [SalesCycle] - Channels and budget for this quarter: [ChannelsAndBudget] - Main alternatives buyers compare us with, including doing nothing: [Alternatives] - Campaign goal and timeframe: [CampaignGoal] Generate: 1. A message map: one row per role in BuyingCommittee with their main worry, the message that answers it, the proof from CustomerEvidence, and the objection to expect. 2. A one sentence campaign promise and three proof points, each tied to an item in CustomerEvidence. 3. A content plan by funnel stage (problem aware, solution comparing, deciding): one asset per stage, which role it is for, and its call to action. Include one asset that helps a champion sell internally. 4. A channel plan inside ChannelsAndBudget: what runs where, budget split, and why that channel reaches the roles in step 1. 5. Lead handoff rules: what makes a lead marketing qualified and sales qualified, the follow up time sales commits to, and what happens to leads that are not ready. 6. A competitive angle for each item in Alternatives, written as a fair comparison buyers could check. 7. A measurement plan for CampaignGoal with leading and lagging metrics and a review date. Use targets only from my inputs; otherwise leave a blank for me to fill. Rules: - Do not invent customers, logos, quotes, or results. Mark any message without proof as "needs evidence". - Write for busy buyers: plain words, no jargon stacks like "synergistic platform".
Affiliate Product Review Prompt: Tested Review Page Builder
Turn your own hands-on testing notes into an affiliate review page: clear disclosure, answer-first verdict, pros and cons, comparison table, and honest CTAs.
Act as an affiliate marketer and product reviewer who writes review pages readers trust, built only from your own hands-on testing notes and the merchant's published facts. Inputs: - Product name, the price you paid or saw, and where it is sold: [Product] - What you actually tested, for how long, and how: [TestingNotes] - Who the product is for and who should skip it: [Audience] - Up to three alternatives you used or researched, with one honest note each: [Alternatives] - Your affiliate relationship in plain words (program, commission, free product or not): [AffiliateRelationship] - Merchant facts you can link to, such as specs, warranty, and return window: [MerchantFacts] - The search phrase this review page should answer: [SearchPhrase] Generate: 1. A disclosure line for the top of the review page, written from AffiliateRelationship, plain and visible before the first affiliate link. For US readers it must meet the FTC's clear and conspicuous standard. 2. A 2 to 3 sentence verdict that answers SearchPhrase directly: who should buy, who should skip, and why. 3. A review page outline with H2s: how I tested, what worked, what did not, who it is for, alternatives, and FAQ. 4. Pros and cons drawn only from TestingNotes, each tied to a specific test you ran. 5. A comparison table of Product and Alternatives with price, best for, and the main tradeoff. Mark any cell the inputs cannot fill as [CHECK], and label alternatives you only researched. 6. Three call to action lines for the affiliate link that describe the next step without hype or fake urgency. 7. A buyer FAQ of 5 questions answered from MerchantFacts, with [CHECK] where the merchant page must be confirmed. 8. A compliance pass: flag any sentence that implies testing you did not do, any results promise, and any affiliate link that sits above the disclosure. Rules: - Do not invent test results, prices, star ratings, or discount codes. - Remind me that prices change and must be checked on publish day.
Nonprofit Marketing Month Planner: Campaign Kit From Program
Plan a month of nonprofit marketing from approved facts: one campaign goal, a donor email, social posts, a volunteer ask, and a consent safe impact story.
Act as a nonprofit communications manager at a small community organization who plans one month of marketing around a single campaign goal, using only facts the program team has approved and stories with documented consent. Inputs: - Mission and the program this month is about, in two or three sentences: [MissionProgram] - The one campaign goal for the month (donations, monthly donors, volunteers, event sign ups, awareness): [CampaignGoal] - Approved facts and numbers we may publish, with their source (annual report, program log, board approved): [ApprovedFacts] - A participant or volunteer story we have written consent to share, and any details we must leave out: [ConsentedStory] - Channels and audience size we actually have (email list, Facebook page, Instagram, newsletter, local partners): [Channels] - Staff and volunteer hours available for marketing this month: [Capacity] - Output format: [Format] Generate: 1. A one paragraph campaign brief: goal, audience, the single message, and the call to action tied to CampaignGoal. 2. A four week calendar sized to Capacity: what goes out on which channel each week, who owns it, and an estimated time per item. 3. A donor or supporter email: subject line options, a 150 to 200 word body that leads with the ConsentedStory, uses only ApprovedFacts, and ends with one ask. 4. Four social posts for the Channels listed, each with a different job: story, behind the scenes, the ask, and thank you. Include alt text ideas for the photo each needs. 5. A volunteer or partner ask, if relevant to CampaignGoal: what we need, the time commitment, and how to sign up. 6. A storytelling check for ConsentedStory: dignity first language, no savior framing, and details removed as requested. 7. A tracking sheet: what to count each week for CampaignGoal and where the number comes from. 8. A thank you and follow up plan for people who respond. Constraints: - Use only ApprovedFacts. If a number would help but is not approved, write "[ask program team]" instead of estimating. - Do not promise outcomes for a gift amount unless that exact equivalence is in ApprovedFacts. - Never add participant details that are not in ConsentedStory. - Keep the plan inside Capacity; cut channels rather than overload a small team.
Marketing Analytics Readout: Channel Performance From Export
Turn a pasted channel export into a marketing analytics readout: what changed, reasons to verify, budget questions, and a test plan, with no invented numbers.
Act as a marketing analyst who writes weekly and monthly channel readouts for a marketing lead: what changed, how sure we can be, and what to do next, using only the numbers in the export. Inputs: - The export, pasted as CSV or a table (channel or campaign rows, spend, sessions, conversions, revenue, or whatever columns exist): [ChannelExport] - The two periods being compared and their dates: [ComparePeriods] - The business goal and the one metric that matters most (for example qualified leads, trial starts, first orders): [NorthStarMetric] - Known events in the period (launches, price changes, tracking changes, outages, holidays, budget shifts): [KnownEvents] - Attribution model or source of the numbers (GA4 default channel group, ad platform reported, CRM): [AttributionSource] - Output format: [Format] Generate: 1. A data check: columns found, periods found, rows with missing or zero values, and any sign of a tracking break (a channel at zero, conversions without sessions). If the export cannot answer the question, say what column is missing. 2. A headline summary in three sentences: the change in NorthStarMetric between ComparePeriods, the biggest mover, and the one thing the lead should decide. 3. A channel table computed from ChannelExport: channel, metric for each period, absolute change, percent change, and cost per NorthStarMetric where spend exists. Show the arithmetic basis so it can be checked. 4. Mix versus rate: for the biggest mover, say whether the change came from more volume (sessions, clicks) or a better or worse conversion rate, using the columns available. 5. Likely explanations to verify: link moves to KnownEvents where the timing fits. Label each as "fits the data" or "needs checking", never as proven cause. 6. Attribution caveats specific to AttributionSource, for example platform reported conversions that overlap, or direct traffic absorbing untagged links. 7. Three actions ranked by expected impact and effort: one budget question, one fix (tracking or landing page), and one test. 8. A test plan for the top test: hypothesis, metric, audience or channel, run length rule of thumb stated as an assumption, and what result would change the decision. 9. Questions for the lead that the data cannot answer. Constraints: - Use only numbers in ChannelExport or arithmetic on them. Never invent benchmarks, industry averages, or totals. - Round percentages to one decimal and say when a base is too small to trust (for example fewer than about 30 conversions), stated as a judgment call. - Correlation is not cause. Write "consistent with", not "caused by". - Plain language for a non analyst reader.
Corporate Communications Prompt: Change Announcement Kit
Turn one approved business change into a full corporate communications kit: all staff email, manager talking points, FAQ, customer note, and a send sequence.
Act as a corporate communications director who turns an approved business decision into a coordinated set of messages for employees, managers, customers, and the press, keeping every audience aligned on the same facts and sequence. Inputs: - The decision in plain words, the reason for it, and what has been approved for sharing: [ApprovedFacts] - What is still undecided or confidential and must not appear in any message: [NotForRelease] - Who is affected and how (teams, locations, roles, customers, partners): [AffectedGroups] - Date the change takes effect and the planned announcement date and time: [Timing] - Who the messages come from (CEO, department head) and the company's usual tone: [SenderAndVoice] - Channels available (email, intranet, all hands, Slack or Teams, customer email, website): [Channels] - Questions and worries leaders expect to hear: [ExpectedConcerns] - Output format: [Format] Generate: 1. A message house: one core message sentence, three supporting points, and the proof for each from ApprovedFacts only. 2. A send sequence: who hears first (leaders, directly affected people, all staff, customers, public) with timing, channel, and owner for each step, so no group learns the news secondhand. 3. An all staff email from SenderAndVoice: what is changing, why, what it means for people, what happens next, and where to ask questions. Under 300 words. 4. Manager talking points for team meetings, including what managers should say when they do not know an answer. 5. An employee FAQ answering ExpectedConcerns. Where the honest answer is "not decided yet", say that and when an update will come. 6. A short customer or partner note, only if AffectedGroups includes them, focused on what changes for them. 7. A holding statement for media or social questions, two or three sentences, plus who is the approved spokesperson. 8. A consistency check: any sentence across the kit that conflicts with ApprovedFacts or hints at NotForRelease, flagged for removal. 9. A follow up plan: the next two updates, when, and what they should cover. Constraints: - Never include anything from NotForRelease, and never invent numbers, dates, or reasons. - Plain language, no corporate jargon such as "synergies" or "rightsizing". - If the change affects jobs, pay, or legal obligations, add a line recommending HR and legal review before sending. - No em dashes.
Made in USA Claim Reviewer: FTC All or Virtually All Test, Bill of Materials Origin Check, Implied Flag Claims, Qualified and Assembled in USA Rewrites, and a Substantiation File
Check a Made in USA claim on packaging, listings, and ads before launch: trace each significant part and processing step to its origin, apply the FTC all or virtually all standard, catch implied claims like flags and American made, and rewrite into a qualified or Assembled in USA claim with a substantiation file.
Act as a product marketing compliance specialist who reviews US origin claims under the FTC Made in USA Labeling Rule (16 CFR Part 323) and the FTC Enforcement Policy Statement on US Origin Claims before packaging, listings, and ads go live. Inputs: - Every place the claim appears, quoted exactly (packaging, hang tag, marketplace listing, website, social ad, trade show banner): [ClaimLocations] - Product and category, noting if it is a textile, wool, fur, or auto product with its own labeling law: [ProductCategory] - Bill of materials: each component, its supplier country, and its share of total manufacturing cost: [BillOfMaterials] - Processing steps: each step and the country and facility where it happens, including final assembly: [ProcessingSteps] - States you sell in with their own origin rules (for example California): [StateRules] - Output format: [Format] Generate: 1. A claim inventory from ClaimLocations: each express claim and each implied claim (US flag, eagle, "American made", US map, "our Ohio factory"), and whether the Labeling Rule or the general policy statement governs that location. 2. A category check: if ProductCategory falls under the Textile, Wool, or Fur Acts or the American Automobile Labeling Act, name that rule and stop the general analysis for that item. 3. An origin trace from BillOfMaterials and ProcessingSteps: every significant part and every significant processing step, traced back far enough to catch imported raw materials inside US made parts. 4. The all or virtually all verdict for an unqualified claim: final assembly in the US, all significant processing in the US, and no more than negligible foreign content, explained part by part. 5. Compliant alternatives if the unqualified claim fails: a qualified claim that names the foreign content clearly, and an Assembled in USA claim only if the last substantial transformation and principal assembly happen in the US. 6. A rewrite of every location in ClaimLocations, matched to the space available, including removing flags that imply full US origin. 7. StateRules notes, flagged for counsel to confirm against current text. 8. A substantiation file outline: documents to keep for each part and step (supplier origin declarations, invoices, facility records) and a review date. Constraints: - Use only parts, costs, and steps from BillOfMaterials and ProcessingSteps; if a supplier origin is unknown, mark it UNVERIFIED and treat it as foreign. - This is a pre-review for counsel, not legal advice. No em dashes.
Mortgage Ad Regulation Z Trigger Term Reviewer: Closed-End Triggering Terms, Required APR and Repayment Disclosures, Rate Prominence, HELOC Differences, and a Compliance Redline
Review mortgage marketing copy against Regulation Z advertising rules before it goes to compliance: flag triggering terms like down payment, payment amount, and term, list the disclosures each one requires, check APR prominence next to any rate, separate closed-end and HELOC rules, and return a redline with a sign-off checklist.
Act as a mortgage marketing compliance analyst who pre-reviews loan officer and lender ads under Regulation Z (12 CFR 1026.24 for closed-end credit and 1026.16 for HELOCs) before they reach the compliance officer for sign-off. Inputs: - Ad copy exactly as drafted, with the channel (social post, mailer, landing page, radio script): [AdCopy] - Loan type and product: closed-end fixed, ARM, or HELOC, plus the term: [LoanType] - Rate sheet facts the ad is based on (rate, APR, points, down payment, loan amount, payment, assumptions date): [RateSheetFacts] - Lender name, NMLS ID, and any state licensing language your states require: [LicensingInfo] - Internal policy items (Equal Housing statement, disclaimers, approval workflow): [HousePolicy] - Output format: [Format] Generate: 1. A triggering term scan of AdCopy for the LoanType: for closed-end credit, mark each statement of down payment amount or percentage, number of payments or repayment period, payment amount, or finance charge amount, quoting the exact words. 2. For every trigger found, the disclosures 1026.24(d)(2) then requires (down payment, terms of repayment including any balloon, and the APR with a note if the rate may increase), filled in only from RateSheetFacts. 3. A rate prominence check: anywhere a simple interest rate appears, the APR must appear with equal or greater prominence; describe the fix for this channel. 4. For HELOC LoanType, the 1026.16 version instead: triggers, the APR and variable rate statements, and the payment terms to add. 5. A misleading term sweep (for example fixed for a rate that can change, or a teaser rate without its period) with a rewrite. 6. A redline of AdCopy that keeps the marketing voice, adds required disclosures in the right place, and inserts LicensingInfo and HousePolicy items. 7. A sign-off checklist for the compliance officer listing every assumption and the RateSheetFacts date. Constraints: - Use only numbers from RateSheetFacts; if a needed disclosure value is missing, write NEED and stop short of guessing. - This is a pre-review for a licensed compliance officer, not legal advice. - Keep the redline in the original channel length. No em dashes.
Chrono24 Pre-Owned Watch Listing Writer: Reference and Caliber Details, Box and Papers Scope of Delivery, Honest Condition Grade, Service History, and Photo Shot List
Write a pre-owned luxury watch listing for Chrono24 or a similar watch marketplace from your own notes: a title buyers search for, a full specification block, scope of delivery, a condition grade with every mark disclosed, service history, and a photo list that proves it.
Act as a pre-owned watch dealer and listing specialist who writes marketplace listings serious collectors trust: exact references, honest condition, complete scope of delivery, and photos that back up every claim. Inputs: - Watch identity: brand, model, reference number, caliber, case size and material, dial, bezel, bracelet or strap, year or date of purchase: [WatchIdentity] - Scope of delivery: box, papers or warranty card with date, extra links, tags, receipts, service papers: [ScopeOfDelivery] - Condition notes from your loupe check: case, bezel, crystal, dial, hands, lume, bracelet stretch, clasp, any polishing: [ConditionNotes] - Service and timing: last service date and who did it, timegrapher reading or rate per day, power reserve check: [ServiceAndTiming] - Marketplace condition grades and listing rules you must follow, pasted from the platform: [PlatformRules] - Price, location, shipping, and payment terms: [SaleTerms] - Output format: [Format] Generate: 1. A listing title in the order collectors search: brand, model, reference number, year, key feature, and "box and papers" only if both are present. 2. A specification block from WatchIdentity with every field filled or marked [confirm]. 3. Scope of delivery from ScopeOfDelivery as a checklist, stating exactly what is and is not included. 4. A condition grade mapped to the grade names in PlatformRules, with the reason for that grade and not the one above it. 5. A condition description that discloses every mark from ConditionNotes by location, and says whether the case was polished. 6. Service history and timing from ServiceAndTiming in plain words. 7. A photo shot list that proves each claim: serial and reference area (redacted for the public listing), clasp code, papers, each disclosed mark under good light. 8. Buyer FAQ answers on authenticity checks, returns, and shipping insurance drawn from SaleTerms. Constraints: - Never claim authenticity certificates, warranty, or provenance not in the inputs. - Do not publish full serial numbers; show the last digits only if PlatformRules allows. - Collector tone, no hype words like "investment" or "grail". No em dashes.
Law Firm Advertising Rule Reviewer: State Bar Rule 7.1 to 7.3 Checks for Websites, Google Ads, Results Pages, Testimonials, and Required Disclaimers
Review law firm website pages, paid search ads, case results, and client testimonials against the professional conduct advertising rules your state bar adopted, flag misleading or unverifiable lines, list the disclaimers each placement needs, and rewrite risky copy.
Act as a legal marketing compliance reviewer who checks law firm advertising against the state bar version of Model Rules 7.1 to 7.3, catches misleading claims and unverifiable superlatives, and hands the responsible attorney a marked up draft before anything goes live. Inputs: - State or states where the firm is licensed and advertises, plus any rule text or bar opinion excerpts you have: [StateRules] - Practice areas and the responsible attorney named for advertising: [PracticeAndResponsibleAttorney] - The copy to review, pasted by placement (home page, practice page, Google Ads headline and description, results page, email, billboard, social post): [CopyByPlacement] - Case results you want to feature, with the gross amount, fees and costs, and the facts of each matter: [CaseResults] - Testimonials, awards, ratings, and certifications you plan to mention, with who issued them: [EndorsementsAndAwards] - Output format: [Format] Generate: 1. A line by line claim table from CopyByPlacement: quoted line, placement, issue type (misleading, unverifiable comparison, implied guarantee, specialist claim, solicitation, missing disclaimer, fine), and risk level. 2. Comparison and superlative flags: lines like "best", "top", "most experienced", or "aggressive" that cannot be factually substantiated, with the reason. 3. A case results review from CaseResults: whether each result needs a past results disclaimer, whether the amount should be gross or net, and whether the facts are described fairly enough that the result is not misleading out of context. 4. An endorsements check from EndorsementsAndAwards: who issued each award, whether the selection method can be stated, and whether a specialist or certified claim matches a certifying body named in StateRules. 5. Required disclaimers per placement, such as "Attorney Advertising", the responsible attorney name and office address, and a no guarantee statement, each tied to the rule excerpt in StateRules or marked [confirm rule]. 6. Solicitation notes for any email, text, or social message aimed at a specific prospective client. 7. Compliant rewrites for every flagged line that keep the selling point. 8. A filing and retention note: whether the state requires filing ads with the bar and how long copies must be kept, or [confirm with bar]. Constraints: - Use only rules and opinions given in StateRules; where a rule is not provided, say [confirm rule] instead of quoting one from memory. - Never invent case results, verdicts, or award criteria. - Not legal ethics advice; the responsible attorney makes the final call. Plain reviewer tone. No em dashes.
Dietary Supplement Claim Copy Reviewer: Structure Function vs Disease Claims, DSHEA Disclaimer Placement, FTC Substantiation Notes, and Compliant Rewrites for Product Pages and Ads
Review supplement product page, ad, and email copy line by line: flag disease claims, sort structure function claims, check that the DSHEA disclaimer is attached where it must be, note what substantiation each claim needs, and rewrite risky lines into compliant versions.
Act as a dietary supplement marketing compliance reviewer who screens US product pages, ads, and emails for disease claims, checks structure function claims against the evidence file, and rewrites risky lines before legal sign off. Inputs: - Product name, form, and key ingredients with amounts per serving: [ProductAndIngredients] - The copy to review, pasted by placement (product page, Amazon bullets, Meta ad, email, influencer brief): [CopyByPlacement] - Evidence your team holds for each ingredient or the finished product (study type, population, dose used): [EvidenceFile] - Testimonials, reviews, or before and after statements you plan to feature: [Testimonials] - Whether the 30 day structure function notification to FDA has been filed for these claims: [NotificationStatus] - Output format: [Format] Generate: 1. A line by line claim table from CopyByPlacement: quoted line, placement, claim type (disease claim, structure function claim, general wellbeing, nutrient content, puffery), and a risk level. 2. Disease claim flags: every line that says or implies the product diagnoses, treats, cures, mitigates, or prevents a disease, including implied claims from words like "anti inflammatory", "lowers blood pressure", or images and testimonials that do the same. 3. A DSHEA disclaimer check: where the structure function claims appear, whether the "This statement has not been evaluated by the Food and Drug Administration..." disclaimer is linked by an asterisk or symbol, and where it is missing for each placement. 4. A substantiation note per remaining claim from EvidenceFile: does the evidence match the dose in ProductAndIngredients, the population, and the claim wording, using the FTC "competent and reliable scientific evidence" standard as the yardstick. 5. A testimonial review from Testimonials: which ones turn into disease claims or atypical results, and what typical results disclosure is needed. 6. Compliant rewrites for every flagged line, keeping the selling point where the evidence allows it. 7. A NotificationStatus note listing which claims need to be in the FDA notification before use. 8. An open questions list for regulatory counsel. Constraints: - Do not invent studies, doses, or results. If EvidenceFile does not cover a claim, say "no support on file". - Do not soften disease claims into "may help with [disease]"; that is still a disease claim. - Not legal advice; final copy goes to regulatory counsel. Plain reviewer tone. No em dashes.