Win & Scale
IndustriesBeauty & skincare

Meta ads for beauty brands, run by your AI agent.

Find the routines that sell, and launch the next test paused. Your agent reads what bought sales and spends nothing until you approve.

7 days free with every feature. Cancel anytime.

Works with

Try asking
  • Which routines sold over the last 90 days?
  • Which numbers in this copy aren’t in our strategy?
  • Brief three ads for the new serum.
  • Launch the texture test, paused.
A four-frame Reel from Saltmilk, a fictional brand, in a phone, with the agent's work around it: Values tagged (Simple nightly routine, Skincare minimalist), a winning creative, a launch built paused and a prompt waiting for the owner to activate it. Four-frame vertical reel for Saltmilk, a fictional skincare brand, following one woman through a four-step night routine.

What does a beauty brand need from Meta ads?

Beauty content piles up faster than anyone can judge it, and one careless claim in a caption can cost the ad.

  • “I can’t tell which routine video sold.”

    Get ready with me, texture close-up, honest review. They live in ad names like Reel_serum_v4, and views are easy to mistake for sales.

  • “Results claims make me nervous.”

    Meta limits before-and-after imagery and health claims, so results claims need care. A bold number in a caption is the easiest line to get wrong.

  • “I can’t film the founder every week.”

    A founder talking to camera often beats the studio shot. Knowing which story earned another take is a guess made on a Friday.

See which routine sold, not which one got views.

Your agent ranks every ad on purchases against the rest of the account. A texture or routine that sold stands apart from one that only got watched.

  • meta_get_evidence_health checks the numbers are fresh, and how much spend is still untagged, before judging anything.
  • meta_get_history_winners judges on purchases over 30 and 90 days, not on Meta’s “Results”.
  • meta_get_audience_breakdown shows which ages and placements still buy from a routine.
A live test for Saltmilk, a fictional brand, day 4 of 7, question frozen, two observations. The selfie has 2 of the 10 purchases its rule asked for, so the reading is inconclusive and too early. Below it, one proposed learning from a concluded test: a delivery date in the first line beats a discount for returning buyers. It counts only once you approve it.

Know what each video says, and what it is.

Win & Scale stores what each creative is as Values: its angle, persona, format and hook. The ad name stays a hint, so a lesson survives the rename.

  • meta_tag_creatives tags each routine, texture shot and founder video with its angle, persona, format and hook.
  • meta_transcribe_creative reads what each video actually says, so a claim shows up in text before it runs.
  • meta_get_cross_analysis compares two of them, such as persona by format.
A Library creative, Saltmilk's UGC selfie (a fictional brand), a static read as an image: its Values are the angle Simple nightly routine, the persona Skincare minimalist, the format UGC selfie and the hook Selfie caption, nightly reset, with the line the agent read, “My nightly skin reset.”, and each trait marked Winner, In line or Low delivery, inconclusive.

Test the hook, not the whole video.

Your agent turns the next idea into a test, with its question frozen up front: what changes, what stays, and how it will be judged. Results are added to the record, never rewritten.

  • meta_suggest_next suggests which routine or founder story deserves the next test slot.
  • meta_create_test writes down the question, and how it will be judged, before any result comes in.
  • meta_conclude_test waits for enough purchases, then files the lesson for the next launch.
The Briefs window on its Tests tab. A suggested test for Saltmilk, a fictional brand: Selfie for the Skincare minimalist, set against the product shot. It says what could mislead it and what would prove it wrong. Committing it calls meta_create_test.

Check the claims. Launch it paused. You turn it on.

Your agent writes briefs from your brand voice and the proof you can claim, then builds the launch with nothing spending. The strategy preflight flags numbers your strategy doesn’t state, and activating is a separate call that waits for you.

  • meta_update_strategy keeps your do’s, don’ts and proof points in one place for every brief.
  • meta_launch_ads builds the campaign, ad set and ads paused, and flags copy your strategy doesn’t back. It is not a policy review.
  • meta_activate spends nothing until you say go. Your agent asks you first.
An agent calls meta_launch_ads for Saltmilk, a fictional beauty brand, and gets back a paused launch: the campaign, the ad set and three ads, all Paused, with Activate waiting for the owner.

What can a beauty brand ask its AI agent?

Ask the way you would ask a media buyer who knows the category. Your agent checks the evidence before it answers.

  • Evidence checkWhich numbers from the last launch shouldn’t I trust yet? Don’t change anything.
  • What soldWhich routines and textures sold over the last 180 days, judged on purchases?
  • Check the claimsWhich numbers in this week’s captions aren’t in our strategy? Don’t change anything.
  • Launch pausedAnswered in the conversation: Launch the texture test for sensitive skin. Leave it paused for me.
  • Read the videosTranscribe this week’s creator videos and tell me which claims they make.
  • Brief the launchBrief three ads for the new serum from what sold, in our brand voice.
Claude Code · winandscale connected

Launch the texture test for sensitive skin: three cuts, one ad set. Leave it paused.

  1. meta_get_strategydo’s, don’ts and proof points read
  2. meta_get_history_winnersTexture · Winner, 90d
  3. meta_launch_ads1 caution on the copyPaused
  4. meta_activateWaiting for you

Built 1 campaign, 1 ad set and 3 texture ads, all paused. One caption quotes a number your strategy doesn’t state, so I flagged it. Fix it or add the proof, then tell me to activate.

What does your agent tag on every beauty ad?

Every ad is tagged with Values: its angle, persona, format and hook. Results compare even when ad names don't.

ValuesYour account’s Values come from your own creatives.

meta_list_taxonomy

  • Angles

    Why someone should buy now

    • Routine
    • Ingredient story
    • Gentle on skin
    • Restock
    • Gift set

  • Personas

    Who the ad speaks to

    • Sensitive skin
    • First serum
    • Busy morning
    • Returning customer

  • Formats

    What the creative looks like

    • Texture
    • Founder
    • Get ready with me
    • Unboxing
    • Studio static

  • Hooks

    The first three seconds

    • Honest review
    • Three-step routine
    • What I stopped using
    • Ingredient explained

Where to go next

Questions, answered

Everything else is in the docs.

Can an AI agent run Meta ads for a beauty brand?
Yes, an AI agent such as Claude Code or ChatGPT can run a beauty brand’s Meta ads with Win & Scale. Your agent reads the ad account, tags each routine and builds the next launch paused.
Does Win & Scale check my skincare ads against Meta’s policy?
No, Win & Scale is not a policy review. Its strategy preflight flags numbers and claims your strategy doesn’t state, and results claims still need your own care.
Can my agent read what creators say about my products?
Yes, Win & Scale transcribes every video in your library. Your agent is also told when a video has only been read from its poster image.
Will my agent launch ads without asking?
No, every launch is created paused. Turning one on is a separate call, meta_activate, and your agent asks you first.
How much does Win & Scale cost for a beauty brand?
Win & Scale starts with a 7-day free trial that includes every feature. After it, each ad account pays a flat monthly price by ad spend, from $49 a month for up to $10k.
Which AI agents work with Win & Scale?
Any AI agent that connects over MCP works with Win & Scale, including Claude Code, Claude, ChatGPT, Cursor and Codex. Agent calls cost 0 AI credits, because they run on your own plan.

Find the routines that sell. Launch the next test paused.

Start a 7-day free trial with your website, connect your AI agent, and keep every launch paused until you say go.

Works with