A personalized welcome video for every club member
Plus a Cowork pricing audit, one bottle shot turned into a video ad, and why on-premise deserves your budget.
Jeremy Young5 min read
Today's Alcohol Industry Insider Newsletter
What's inside:
💡 AI Prompts You Can Use: One script, a HeyGen avatar, and a personal welcome video for every new club member
💡 AI Prompts You Can Use: One prompt that builds your next 90 days of email, drafts included
💡 AI Prompts You Can Use: Find your underpriced SKUs: a Claude Cowork pricing audit by channel
🛠️ Try These Tools: Turn one bottle shot into a 15-second video ad with Pollo AI
🥊 Wrong Take: Stop treating the on-premise as the first budget you cut
One script, a HeyGen avatar, and a personal welcome video for every new club member
The outcome: a 45 to 60 second welcome video that greets a new club member by name, tells them what is coming in their first shipment, and gives them one thing to do next. You write the script once with Claude, then let a HeyGen avatar record each personalized version so nobody has to stand in front of a camera again.
What this replaces: the "we should really do a welcome video" item that has been on your list since last spring, plus the generic confirmation email that gets archived in four seconds. A brewery can use the same setup for a membership or mug club, a distillery for a barrel-pick or bottle-share club, a retail shop for a monthly wine subscription, and a distributor rep for a short "here is what we just shipped you and how to sell it" clip to a new account.
Tool and difficulty: Claude (claude.ai) writes the script, HeyGen (heygen.com) makes the video. Medium: you need to paste in your own club details, and HeyGen's free plan allows 3 videos a month up to 1 minute each with 1 custom avatar and a watermark. Creator is $29 a month, or $24 a month billed yearly, with 600 credits a month and 1080p (checked on heygen.com October 12, 2026). Check heygen.com before you count on a feature.
Set it up
Decide who the on-camera person is: owner, winemaker, head brewer, club manager. If you want a custom avatar of a real person, record them reading a short piece of copy on a phone in good light and upload it to HeyGen. Get written consent first.
If you would rather skip that, pick a stock avatar in HeyGen and a voice that fits your brand.
Pull your club facts into one place: tier names, shipment months, member benefits, pickup or shipping policy, and the single action you want a new member to take first.
Run the prompt below in Claude to get the script with a swappable name slot.
Paste the script into HeyGen, choose your avatar, and generate one test video using a fake member name.
You are a direct-response copywriter who writes for small beverage brands. You write the way people actually talk, not the way marketing departments write.
Write a 45 to 60 second welcome video script for a new member of our club. The script will be read on camera by an AI avatar, so it must sound natural when spoken out loud, use short sentences, and avoid any word that is hard to say.
Here is my business:
- Business name: [BUSINESS NAME]
- Type: [WINERY / BREWERY / DISTILLERY / SHOP]
- Region: [REGION]
- On-camera person and role: [ON-CAMERA PERSON AND ROLE]
- Club name: [CLUB NAME]
- Tiers and what each one gets: [TIER NAMES AND BOTTLE OR CAN COUNTS]
- Shipment months: [SHIPMENT MONTHS]
- Top three member benefits: [TOP 3 MEMBER BENEFITS]
- Pickup or shipping policy: [PICKUP OR SHIPPING POLICY]
- The one action I want a new member to take first: [FIRST ACTION YOU WANT THEM TO TAKE]
- Our brand voice in three words: [BRAND VOICE IN THREE WORDS]
Structure the script in this exact order:
1. Greeting with the member's first name in the first six seconds. Use the literal placeholder {{FIRST_NAME}} so I can swap it per member.
2. One sentence of thanks that does not sound corporate.
3. One specific, concrete detail only our club would know: the vineyard block, the barrel, the brew day, the still run, the person who packs the boxes. Ask me for this detail if I did not give you enough to work with.
4. What happens next: when their first shipment goes out, what is in it, and how pickup or shipping works.
5. One benefit they would not expect.
6. A single clear ask tied to my first action, said once, with no second ask stacked on it.
7. A warm sign-off of one sentence.
Rules:
- Total spoken length 45 to 60 seconds at a normal speaking pace. Count it and tell me the estimated run time.
- No tasting notes, no scores, no awards.
- No phrases like "we are thrilled" or "welcome to the family."
- Write at a level a guest in the tasting room would understand with no wine, beer, or spirits background.
Deliver three things:
A. The script, formatted as plain spoken text with {{FIRST_NAME}} where the name goes.
B. A line-by-line list of where the speaker should pause or change tone, so the avatar does not sound flat.
C. Three alternate opening lines I can test, each a different angle (personal, behind-the-scenes, surprising fact about our club).
Then ask me one question: what is the single thing new members most often get confused about in their first month, so you can work the answer into the script.
Variables to swap: [BUSINESS NAME], [WINERY / BREWERY / DISTILLERY / SHOP], [REGION], [ON-CAMERA PERSON AND ROLE], [CLUB NAME], [TIER NAMES AND BOTTLE OR CAN COUNTS], [SHIPMENT MONTHS], [TOP 3 MEMBER BENEFITS], [FIRST ACTION YOU WANT THEM TO TAKE], [BRAND VOICE IN THREE WORDS], [PICKUP OR SHIPPING POLICY].
What to do with the output
Generate the video, then drop it into your welcome email or text as the first thing a new member sees. If you are on the free plan, make three videos for your three highest-value new members this month and send the generic version to everyone else. On a paid plan, batch them: swap the name line, regenerate, and queue the week's new signups every Friday in one sitting.
Rerun the script prompt every time your club changes, which for most of you is twice a year when the lineup or the shipment schedule moves. Keep the old script in a Claude Project with your club details so the next version takes five minutes instead of an hour.
If the first draft reads like a press release, tell Claude: "Rewrite this the way [NAME] actually talks to a guest across the bar. Shorter sentences. Cut every adjective you do not need."
Good output sounds like one person talking to one person: the member's name in the first six seconds, one concrete detail only your club would know, and exactly one thing to do next. If it could be sent by any club in your state, it is not done yet.
One prompt that builds your next 90 days of email, drafts included
Outcome: a 90-day email calendar mapped to your releases, holidays, and club shipments, with send dates, audience segments, subject lines, preview text, and a usable first draft of every email.
Tool: Claude (claude.ai). Works in a normal chat. Difficulty: Medium (you paste in your own dates and offers). Cost: Claude's free plan handles this, Projects included (up to 5). If you hit the free limits, Claude Pro is $20 a month, or $17 a month billed yearly (claude.com/pricing, October 12, 2026).
One setup step that makes this much better. In Claude, create a Project and drop in your brand voice notes, your price list, and your club tiers. Everything you write in that project uses them as standing context, so you stop re-explaining your business every time. If you skip the project, paste that detail straight into the prompt.
Before you start, write down three things: your release dates for the next quarter, your club shipment and billing dates, and the holidays or local events that actually move volume for you. A brewery might list a seasonal can drop and a taproom anniversary. A distillery might list a single-barrel release and Father's Day. A retail shop might list a Thanksgiving wine guide and a New Year's sparkling push.
You are my DTC email strategist for a beverage business. You have run email programs for wineries, breweries, and distilleries, and you care about revenue per send and unsubscribe rate, not open rate vanity.
MY BUSINESS
- Business type and name: [BUSINESS TYPE AND NAME, e.g., a 4,500-case winery in Walla Walla / a 12-barrel brewery with two taprooms / a craft rye distillery with a bottle shop]
- Region: [REGION]
- Email list: [LIST SIZE AND SEGMENTS, e.g., 6,200 total: 480 club members, 1,900 past purchasers, 3,800 never purchased]
- Brand voice: [BRAND VOICE, e.g., dry humor, no wine jargon, first person from the winemaker]
- Goal for the quarter: [GOAL, e.g., $85,000 in DTC revenue and 60 net new club members]
THE CALENDAR INPUTS
- Releases: [RELEASE DATES AND WINES/BEERS/SPIRITS, e.g., March 6 estate Albarino, April 18 single-barrel bourbon, 220 cases]
- Club shipments and billing dates: [CLUB SHIPMENT AND BILLING DATES]
- Holidays and local events: [HOLIDAYS AND LOCAL EVENTS, e.g., Mother's Day, barrel tasting weekend, county fair]
- Current offers I can use: [CURRENT OFFERS, e.g., free shipping on 6 bottles, $10 tasting fee waived with purchase]
- Shipping cutoffs and weather holds: [SHIPPING CUTOFFS]
STEP 1: Build the 90-day calendar as a table with these columns: send date, day of week, campaign name, audience segment, purpose (acquire, convert, retain, reactivate), primary CTA, subject line, preview text. Cap it at two sends per week. Never send a promotional email within 48 hours of a club billing date, and tell me when you moved something for that reason.
STEP 2: Under the table, list the three sends you expect to drive the most revenue and why, and the two sends you would cut first if my team runs out of time.
STEP 3: Ask me to approve or edit the calendar before you write anything else. Do not write drafts yet.
STEP 4: Once I approve, write full first drafts for the month I name. Each draft: subject line, preview text, 120 to 200 words of body copy, one clear CTA button label, and a plain-text version for the club segment. Write like a person who works here, not a marketing department.
RULES
- No health claims about alcohol. No "cheers to" openers. No exclamation points in subject lines.
- Subject lines under 50 characters, and name the actual product where possible.
- Vary the send types: pure story emails and member-only notes count, not every email is a sale.
- If I have given you a thin or unrealistic input (too few releases, a goal my list size cannot support), say so directly and tell me what you would change.
- Flag any email that needs an asset I have not mentioned (a photo, a video, a landing page) in a short production list at the end.
Variables to swap: [BUSINESS TYPE AND NAME], [REGION], [LIST SIZE AND SEGMENTS], [BRAND VOICE], [RELEASE DATES AND WINES/BEERS/SPIRITS], [CLUB SHIPMENT AND BILLING DATES], [HOLIDAYS AND LOCAL EVENTS], [CURRENT OFFERS], [SHIPPING CUTOFFS], [GOAL].
What to do with the output: ask Claude for the calendar first. Argue with it. Cut sends where you feel crowded, move dates that collide with billing, then say "now write the full drafts for weeks 1 through 4." Work a month at a time so drafts stay sharp. Paste each draft into Klaviyo, Commerce7, Mailchimp, or whatever you use, and have one human read every subject line out loud before scheduling.
Good output looks like this: no more than two emails in any week that contains a club billing date, every send tied to a specific date and segment, and subject lines under 50 characters that name a wine, beer, or spirit instead of saying "Exciting news from the cellar."
Find your underpriced SKUs: a Claude Cowork pricing audit by channel
The outcome: a report that names which of your SKUs are priced too low for what they sell, which are priced too high for how slowly they move, and which ones belong in a bundle instead of a discount.
Tool: Claude Cowork (now part of Claude), in the Claude desktop app. Difficulty: Advanced, because it reads your files. Cowork needs a paid plan: Claude Pro runs about $20 a month, or about $17 a month billed yearly. Check Anthropic's pricing page before you buy.
Set it up in five minutes
Make a folder on your computer called Pricing Audit.
Export your sales as CSV or Excel into it. Pull everything you have: tasting room or taproom POS, e-commerce, club or subscription shipments, wholesale invoices, distributor depletion reports. A retail shop can export register data by item. A distributor can export by brand and account type.
Make sure each file has, at minimum, SKU or item name, channel, units sold, gross revenue, discounts or comps, list price, and a date. Add cost per unit if you have it.
Open the Claude desktop app, start a new Cowork prompt, and point it at the Pricing Audit folder.
Paste the prompt below and let it work.
You are a beverage pricing analyst who has set pricing and promotion strategy for wineries, breweries, distilleries, and their distributors. You are rigorous, and you do not hand me generic advice.
Read every spreadsheet in this folder. It contains my sales history.
My situation:
- Business type: [BUSINESS TYPE, e.g. 9,000-case estate winery, 4,500-barrel brewery, craft gin and vodka distillery, independent wine and spirits retailer]
- Channels in the data: [CHANNELS, e.g. tasting room, website, wine club, wholesale to two distributors, farmers market]
- Period to analyze: [DATE RANGE, e.g. January 2025 through December 2025]
- Gross margin target per unit: [MARGIN TARGET, e.g. 65% DTC, 45% wholesale]
- Do I have cost data: [COST DATA AVAILABLE: yes, cost per bottle is in the file / no, estimate nothing and say so]
- Inventory notes: [INVENTORY NOTES, e.g. 1,100 cases of the 2023 Sauvignon Blanc still in the warehouse, next vintage lands in May]
- Constraints I cannot break: [PRICING CONSTRAINTS, e.g. distributor FOB locked through June, state minimum pricing rules, no discounting on the reserve tier, club members get 20% off everything]
- Currency: [CURRENCY]
Before you analyze anything, tell me in plain language what files you found, what columns you mapped to SKU, channel, units, revenue, discount, and list price, and anything you could not read. If columns are ambiguous, ask me up to five questions and wait for my answers.
Then produce:
1. A SKU by channel table: units sold, list price, effective price after all discounts and comps, discount depth as a percent, revenue, and margin per unit if cost data exists.
2. Underpriced SKUs. Any item selling through quickly at or near full price with little discounting and low inventory left. For each one, give the evidence, a specific proposed new price, and the annual revenue impact at current volume if nothing else changes.
3. Overpriced SKUs. Any item that only moves when discounted, sits at high inventory, or carries deeper discounts than the rest of the lineup. For each one, give three options: hold the price and cut distribution, reprice to a specific number, or move it into a bundle. Say which you would pick and why.
4. Bundle candidates. Pair slow movers with fast movers from my actual lineup. For each bundle, give a name, the SKUs in it, the bundle price, the implied discount versus buying separately, margin per bundle, and which channel to sell it in (club add-on, tasting room takeaway, holiday three-pack, variety case for wholesale).
5. Channel conflict flags. Where the same SKU sells at meaningfully different effective prices across channels, flag it and say which price is training customers to wait.
6. A 90-day action plan: what to change in week one, what needs a price sheet update, what needs distributor notice.
7. What data is missing that would sharpen this, and exactly which export would fix it.
Rules: label any conclusion based on fewer than 50 units as low confidence. Never recommend a discount as the default answer; treat bundling, pack changes, and channel shifts as the first tools. Use my real SKU names throughout. Show your math on every proposed price.
When the analysis is done, save the tables as an Excel file and the findings as a two-page Word memo written for an owner, not an analyst.
Variables to swap: [BUSINESS TYPE], [CHANNELS], [DATE RANGE], [MARGIN TARGET], [COST DATA AVAILABLE], [INVENTORY NOTES], [PRICING CONSTRAINTS], [CURRENCY].
What to do with the output: ask Cowork to save the tables as an Excel file and the findings as a two-page Word memo, then bring the top three moves to your next pricing meeting. Run the bundle candidates past your DTC manager before you build the offer.
Good output names real SKUs with real numbers: "this bottling sold 412 units at an effective price 14% under list in the club channel while full price in the tasting room," not general pricing advice.
Turn one bottle shot into a 15-second video ad with Pollo AI
What it is: Pollo AI is a browser-based image and video platform. Per OpenAI's write-up on the company, it serves more than 26 million users and is built around templates and guided workflows rather than model-picking. Two pieces matter for beverage marketers. Photo to Video Ads, inside its Marketing Studio, turns a still product photo plus a prompt into a short video. Pollo Agent takes rough ideas and reference images and develops storylines, scene flow, and scripts for you. Founder and CEO Bill Zhu told OpenAI the goal is "to do for video what Canva did for design."
Who it is for: DTC and ecommerce leads who need fresh ad creative every week, tasting room managers who post Reels, brand managers at a distillery with one good bottle shot and no production budget, shop owners announcing a new allocation, and distributor reps who want a 15-second clip to send accounts alongside the sell sheet.
The first job: Take the existing studio shot of your best-selling SKU. Upload it to Photo to Video Ads, describe the mood, setting, and lighting in two or three sentences, and generate a short clip. OpenAI's write-up describes a fragrance brand doing exactly this: one still photo became a roughly 15-second ad with velvet textures, warm spotlights, close-ups of the bottle, and a final frame against deep red fabric. A beverage brand used Pollo Agent to turn a plain soda bottle shot into a snowy miniature landscape for a campaign.
Cost and setup: Pollo AI has a free plan with 20 credits, enough for about four 5-second clips on its Pollo 2.5 model at 720p, according to its pricing page as of October 12, 2026. Paid plans start with Lite at $15 a month for 400 credits (up to 80 videos) with watermark-free output, and Pro at $29 a month for 800 credits. Paying yearly brings Lite to $12 a month and Pro to $14.50 a month, which Pollo labels a flash sale, so confirm the price on the page before you buy. Setup is an account, then the Marketing Studio section, then your photo and your prompt. No engineer, no software install.
The catch: Pollo's core audience is content creators making micro dramas, with marketers and business owners described as a newer group. Expect to regenerate a few times. Watch your label: AI video can warp text and logos, so play the clip back frame by frame and confirm the brand name, vintage, and ABV all read correctly before anything goes to a paid ad or a distributor.
Pick one SKU, write down the single feeling you want the clip to produce (crisp, cozy, celebratory), and generate three versions this week. Run the best one as an email header and the next best as a Reel, then compare clicks.
You are a DTC video ad director who makes short product films for wine, beer, and spirits brands. I am going to upload a still product photo into an AI photo-to-video tool and I need the written prompt that goes with it.
My situation:
- Product: [e.g., 2024 estate Albarino, 750ml / barrel-aged imperial stout, 16oz can / small-batch rye, 750ml]
- Brand feel in three words: [e.g., coastal, salty, unfussy]
- The photo I have: [e.g., bottle on white seamless, studio lighting, label facing camera]
- Where this runs: [e.g., Instagram Reels, DTC email header, tasting room screen, distributor sell-in email]
- Length: about 15 seconds
- The one thing a viewer must remember: [e.g., this is the oyster wine / this is our first rye release]
Give me three separate prompts I can paste in, each a different mood (one clean and premium, one warm and social, one unexpected and playful). For each one, write it as a single paragraph the tool can follow, and cover: the setting and surfaces around the bottle, the lighting, the camera movement across the clip, any motion in the scene (condensation, pour, steam, wind), and the final frame. Keep the label facing camera and readable in at least half the shots.
Rules: no people's faces, no drinking on camera, no health or taste claims, no text overlays I would have to fix later. Name beverage-specific details, not generic product-ad language.
Then push back on me: tell me which of the three is wrong for my channel and why, and what single detail in my brief is too vague for the tool to render well. If any idea needs a shoot, props, or a location I would not already have, replace it with something I can do from the photo I described.
Stop treating the on-premise as the first budget you cut
The conventional move when volumes drop is to protect retail and pull back on restaurants and bars. The argument is a good one. Off-premise is where the cases are. One chain buyer decision can move more volume than a year of restaurant calls. On-premise accounts order a case or two at a time, beverage directors turn over constantly, payment terms stretch, and every placement needs staff training that evaporates when the staff leaves. Cost to serve per case is brutal, and in a contraction, cost to serve is what gets scrutinized.
That logic is sound right up until you look at where demand actually went. SipSource data reported by WSWA shows on-premise wine and spirits volume and revenue each down 2.4% over the latest 12 months. Off-premise volume fell 7.5% and revenue 6.7%. Liquor stores were down 7.3% in revenue and grocery down 6.2%. The gap between channels is roughly five points of volume.
The honest counterargument: on-premise is the smaller pool, and it cannot absorb what off-premise lost. True. You are not replacing retail volume with BTG placements. You are deciding where the next sales day, sample case, and incentive dollar goes, and the data says the restaurant and bar channel is holding the consumer you still have.
The price data points the same direction. SipSource shows 61% of spirits volume sits below $20 and only 6.5% at $50 or higher, with the $20 to $29.99 tier more resilient. In wine, tiers at $16 and up held up better, and the $20 to $29.99 tier posted 0.9% revenue growth over the latest 12 months. Prosecco, Sauvignon Blanc, and Champagne all grew revenue in the latest three-month period.
Here is what I would do this week. Pull your account list and count how many selling days went to on-premise last quarter. Pick ten accounts and build the pitch around your $16 to $30 wine or $20 to $30 spirit, not your flagship. Retail shops: rebuild the by-the-bottle set around those same tiers and the sparkling and Sauvignon Blanc that are moving. Breweries, the SipSource figures cover wine and spirits only, so run the same channel split on your own depletion data before you shift anything.
You are a beverage alcohol channel strategist advising a [winery / distillery / importer / distributor sales manager / retail wine and spirits shop] in [state or market]. I am deciding how to reallocate selling effort between on-premise and off-premise for the next 90 days.
Here is my situation:
- Portfolio and price points: [list your top 5 SKUs with FOB and shelf or menu price, for example estate Sauvignon Blanc $24 shelf, small-batch bourbon $27 shelf]
- Current split of selling days: [for example 70% off-premise, 30% on-premise]
- Sales team: [number of reps, in-house or distributor-led, territory size]
- Sample and incentive budget for the quarter: [dollar amount]
- Accounts I already have: [number of chain retail, independent retail, restaurants, bars]
- What is actually depleting: [paste last quarter's depletion or sales data by SKU and channel, or describe it]
Produce the following:
1. A channel reallocation recommendation with a specific new split of selling days, and the math behind it using my own numbers, not industry averages.
2. A target list structure: how many on-premise accounts to pursue, what type (neighborhood restaurant, hotel bar, steakhouse, wine bar, cocktail bar), and which of my SKUs fits each type and why.
3. For each of my top 3 SKUs, the single on-premise placement to chase (by-the-glass, well pour, cocktail list, bottle list) and the price point that makes the account's margin work.
4. A staff training one-pager per SKU: three things a server or bartender can say in ten seconds that would make a guest order it.
5. What I should keep doing in off-premise, specifically, so I do not abandon a channel that still pays the bills.
6. The three ways this reallocation could backfire, and the early warning sign for each.
Rules: use only the numbers I gave you. If a recommendation depends on data I did not provide, say so and tell me exactly what to pull. Do not suggest anything that requires hiring. Push back if my price points do not support on-premise margins, and tell me what price they would need to be. If any step takes more than 90 days to show results, flag it and give me a version I can run this month instead.
From the Editor:
I am always open to consulting, implementation, or brainstorming sessions. Just respond to this email, and I will get back to you shortly.
Alcohol Industry Insider Newsletter: the three-times-a-week growth newsletter for wine, beer, and spirits businesses that need smarter marketing, better sales, practical AI tools, and clear ideas they can implement now.
By Jeremy Young: serial entrepreneur, growth marketer, wine critic, and beverage industry insider.
Respond to this email with questions, ideas, or opportunities, and I will get back to you shortly!
Until next time,
Jeremy
Share This Newsletter
If you found this content useful, please share it with your colleagues and friends…
Your personal link (every colleague who subscribes through it counts toward your rewards):
👉 https://alcoholindustryinsider.com/subscribe
Get the next one in your inbox.
Free, mondays, wednesdays, and fridays. Five minutes to read.