№17 · Bot Profile · Design / Merchandising
Trend Scout Bot
Sort trend noise into “fits my brand” or “skip”.
Paid once. Checkout by Polar, our merchant of record, which works out any sales tax or VAT.
In these sets: All-Access, $49
Or included in membership.
- Format
- Bot Profile
- Made for
- Solo founders, small brands, creators with their own label
- Difficulty
- Beginner
- Time to value
- ~30–45 min
Times are estimates until a platform test run confirms them.
CompatibleChatGPT · Claude · Gemini · Grok
AdaptedAny model: describe trends in text, no screenshots
Overview
- The problem
- “My feed is full of trends, and customers ask for things I don’t make. I can’t tell which ideas fit my brand and are worth a small test, and which I should ignore.”
- What you get
- A monthly trend scout note: each trend or request you collected scored against your brand bible and what your customers actually asked for, sorted into Test small / Watch / Skip, with one small, low-risk test idea for each “Test small” pick and the evidence behind it.
- What’s included
- Bot profile instructions
- Trend capture log (sheet: what you saw, where, date, link)
- Brand-fit scorecard (aesthetic, customer, price tier, can you make it, timing)
- Customer-request log template
- Test / Watch / Skip note template
- “small test” idea guide (pre-order, one colorway, restyle what you already have)
- 3 starter prompts (+ full prompt set)
- Review checklist
- Platform setup notes
- Ready-made skill (SKILL.md folder + zip)
- PDF guide
- Illustrative example
- What you’ll need
- Brand bible or a few lines on your aesthetic and customer
- 5–20 trend observations you collected yourself (screenshots of public posts or notes, with source and date)
- Real customer requests or comments (anonymized)
- What you can actually make or source, and your lead times
- Optional: your own sales by style (or Hero Product Finder output)
How it runs
7 steps- Load your brand bible and capture log
- Bot groups similar observations into trends and notes how much evidence you collected for each
- Bot scores each one on the brand-fit scorecard
- You confirm or change every scoreYour call
- Bot sorts into Test small / Watch / Skip and drafts one small test per “Test small”
- You choose what (if anything) to testYour call
- Re-run monthly. Watch items carry over
Your call marks a step where you review and decide. Nothing moves on without you.
Estimated time: ~30–45 min for a first monthly scout of 5–20 observations.
Starter prompts
- Score these trends against my brand bible
- Which customer requests come up most?
- Give me one small test for this trend
The full prompt set is in the kit.
Sample output
Illustrative, fictional brand “Marlow & Pine”, written for this kit, not a platform test: “Trend: oversized ‘grandpa’ cardigans in brown tones. Evidence: 7 of your 18 saved posts + 3 customer DMs asking for ‘longer, bigger’ knits [your logs, Oct]. Fit: aesthetic GOOD · price tier GOOD · can make it: YES (Coastal Cardigan pattern, longer body [VERIFY with your knitter]) · timing: your lead time 6 wks [VERIFY]. → Test small: pre-order a long-length Coastal Cardigan in one brown, capped at your MOQ. Trend: sheer mesh tops. Fit: aesthetic WEAK (bible: ‘quiet, warm, natural fibers’). → Skip.”
It will be replaced with real output after a test run.
Platforms
| AI tool | Label | Setup note |
|---|---|---|
| ChatGPT | Compatible | Project setup, reads screenshots |
| Claude | Compatible | Project or skill. Reads screenshots, can’t generate images |
| Gemini | Compatible | Skill |
| GrokRuns as a Grok Bot (beta) | Compatible | No limits noted |
| Any modelAny capable chat model | Adapted | Describe trends in text, no screenshots |
We ran it ourselves on this tool. Shows the date and model of the run.
No piece carries this yet. Tested means we have run it ourselves. We update the label as each piece is tested.
Built to run on this tool. Not yet confirmed by our own test run.
Works with a limit we name.
Tools required
Any chat model (one that reads images helps for screenshots). Spreadsheet for the capture log.
House standards for this piece
All our standards- Human review gate
- You confirm every score and choose what, if anything, to test. Nothing is ordered or produced from the bot’s note.
- Data grounding
- Only the owner’s collected observations (with source + date), anonymized customer requests, brand bible and production limits. [LOW EVIDENCE]/[GUESS]/[VERIFY] on gaps.
- No invented results
- No trend forecasts, no “this will sell” or sell-through claims. BoF/McKinsey are context only.
- AI disclosure
- Internal planning note. AI-assisted and owner-reviewed.
- IP & bias
- Trends only. No copying another brand’s designs, prints, logos or imagery. Screenshots are for private reference, never reposted. Inclusive size range in any test idea.
- Privacy
- Remove customer names, handles and order details from request logs. Don’t paste private DMs from other people.
- Approval boundary
- Never browses or scrapes social platforms, posts, contacts suppliers or customers, or places orders.
Questions people ask
Does it know what’s trending right now?
No. It has no live trend data and doesn’t browse. It only knows what you put in your capture log. That keeps it honest: every call traces to something you saw or a customer asked for.
Can I show it screenshots?
Yes, on tools that read images (ChatGPT, Claude). Keep them as private reference. Never repost them. On other tools, describe what you saw in words.
Will it tell me what will sell?
No. It says “worth a small test” or “skip”, never “this will sell”. A small test (a pre-order, one colorway, a capped quantity) is how you find out.
Can it help me make a version of a post I saw?
It will describe the trend (a shape, a color family, a way of wearing something), never copy a specific design, print, logo or garment.
Which AI tool should I use?
Whichever you already use. Tools that read screenshots save you describing posts. Any chat tool works with text descriptions. ChatGPT, Claude, Gemini and the any-chat-tool route work on free plans. Grok Bot needs a paid plan that includes it: The X Subscription Premium, Super or Ultra (Plus and Free don’t include it), or an existing SuperGrok, SuperGrok Plus, SuperGrok Heavy, paid Cursor or Cursor Teams plan.
Can I use it commercially?
Yes, for your own brand. The kit is licensed for one business (you and anyone who works on your business may use it). It’s not licensed for agency or client-service use, and please don’t resell or republish it.
In these sets
Pairs with
- One-Person Brand Bible BuilderInterview yourself into a brand bibleFree
- Hero Product FinderFind the 1–2 pieces that can carry your brand$7
- Small-Batch Drop PlannerPlan a capsule drop from buy to sell-through review$12
- Product Shoot Planner Prompt PackMoodboard, shot list and brief for a lean product shoot$5