For store owners who are also the marketing team

Your store just hired a marketing brain.

One living document about your store. Sixteen agents that read it, do the work, and hand you the result. Nothing spends or sends without your tap.

The brain: six layers, read by every agent, written back to after every run.

You paste. You get. You ship.

  • Runs in your own ChatGPT or Claude
  • Shopify first, any store at level 1
  • Approval before anything spends or sends
  • USD and INR, one time price

You are the marketing team.

And the founder, and the buyer, and support. So the store page has not changed since launch, the ads are the same three you made in March, and last week's numbers live in your head.

ChatGPT helps, until it forgets who your customer is by the third prompt. Every answer is generic because it knows nothing about your store. You end up re explaining your brand every morning.

  1. Generic by default

    A chatbot with no memory of your store writes copy that fits any store in your category. That is the copy your competitors are also pasting.

  2. Nothing gets shipped

    Ideas pile up in a chat window. The product page, the ads, the emails and the creator list all wait for a version of you with a free afternoon.

  3. Nobody learns

    Last week's win is not written down anywhere. So next week starts from zero again.

StoreCrew fixes the memory first. Then it puts a crew on top of it.

What a crew is.

Sixteen specialists that share one memory of your store and never start from a blank prompt.

  • One brain, read firstEvery agent opens the brain before it works: who buys, what they say in reviews, which claims you are allowed to make, what worked last month.
  • A written job per agentEach agent has a job, a step by step workflow, quality gates and guardrails you can read on its page. Store Fix scores your store against a 330 point checkpoint library. Ad Creative ships a claims ledger with every batch.
  • Write back afterWhat an agent learned goes back into the brain, dated and sourced. Learnings are append only. The brain gets smarter every week you run it.
  • Your tap on anything that mattersAnything that spends money, sends a message or changes your store waits for one approval. No approval, no action.
StoreCrewbot
Store Fix Approval

Apply 7 content changes to 4 live products? Here are three of them.

  1. Product description, hero product 1Premium quality. Order now.Uses the phrase your reviews repeat most. Names the objection your FAQ never answered.
  2. SEO title, hero product 2Product 2Product 2 in the words customers search for, under 60 characters.
  3. FAQ metafield, hero product 3emptyQuestion taken verbatim from customer.objections, answer inside claims_allowed.

Previous values recorded. One live batch per day. Token expires in 24 hours.

ApproveHold
Example approval card. What "your tap" looks like in Telegram.

The difference in one line

A marketing brain that informs

Writes a document a human reads, then the human does everything.

StoreCrew

Writes the document, puts sixteen agents on it, gates the risky moves behind your tap, and writes results back.

Sixteen agents. One brain. Your rules.

Every card opens the agent's full page: what it reads, what it does step by step, what waits for your tap, and an example of what it hands you.

The Brain Builder is included with every tier. It writes version 1 of your brain from your storefront, your public reviews and six answers from you. It is part of the brain, not one of the sixteen.

How the brain works.

A versioned document about one store. Six layers. Every agent reads it before it works and writes back after.

  1. Identity
    Positioning in one sentence, your voice with example sentences from your own copy, the claims you are allowed to make and the ones you are not.
  2. Customers
    Who buys, their objections in their words, and the vocabulary lifted verbatim from your reviews.
  3. Products
    Catalogue summary, hero products, price bands, bundles, seasonality.
  4. Competitors
    Three to five named stores, snapshotted weekly so changes can be diffed, never guessed.
  5. Performance
    Last week, trends, channel share. Written only by the Weekly Brain Update and only when it has your numbers.
  6. Learnings
    What worked, what did not, and the decisions log. Append only, dated, sourced.
Brain: your storev12

identity.positioning

Positioning in one sentence, your voice with example sentences from your own copy, the claims you are allowed to make and the ones you are not.

customer.objections

Who buys, their objections in their words, and the vocabulary lifted verbatim from your reviews.

product.hero_products

Catalogue summary, hero products, price bands, bundles, seasonality.

competitors.watched

Three to five named stores, snapshotted weekly so changes can be diffed, never guessed.

performance.last_week

Last week, trends, channel share. Written only by the Weekly Brain Update and only when it has your numbers.

learnings.what_worked

What worked, what did not, and the decisions log. Append only, dated, sourced.

learnings.decisions_log append

[date] [store-fix] Applied 7 content changes to 4 products after approval. Previous values in changes.json.

Example brain document. Section names are real, the text describes what each holds. Every write is dated and sourced.
  1. Build once

    The Brain Builder crawls your storefront and public reviews, asks you six questions, and writes version 1. It marks what it inferred and names what looks wrong.

  2. Read before every run

    Store Fix reads your objections and allowed claims. Ad Creative reads what worked. Creator Outreach reads who buys.

  3. Write back after

    Every run appends dated learnings. The brain gets smarter instead of staying a document.

If your brain has fewer than 20 reviews to draw on, it says vocabulary pending rather than inventing customer language. A summary with zero uncertainty is rejected as overconfident.

Three modes. One upgrade path.

Start with the brain in your own AI. Connect your tools when you want the crew to apply things. Go hosted when you want it to run on a schedule.

  1. Advise

    You paste. You get. You ship.

    Runs inside your own ChatGPT or Claude on your tokens. No credentials, nothing connected. The agent reads the brain, does its job, and hands you copy, lists and files you paste yourself.

    You: You paste the brain and the agent. You copy the output into your store, your ad account, your email tool.

    Brain + Crew
  2. Act

    It drafts. You tap. It applies.

    Connected to your store and tools on your own keys. The agent drafts, then every write waits for one tap: one approval per batch of content changes, one per email batch, one per campaign activation.

    You: You read a card that shows three samples and the full count. You tap approve or hold.

    Connected
  3. Autonomous

    It runs. It sends. You read.

    Scheduled and hosted by us on our infrastructure and tokens. Store Fix re audits every Sunday. Ad Growth reads the account every morning. The Weekly Brain Update lands Monday 06:00. Anything that spends or sends still waits for your tap. That gate never relaxes.

    You: You read the Monday brief and tap the approvals in Telegram.

    Hosted

Every agent page shows what changes for that agent between the three modes.

Pick how much you want to do yourself.

One time prices for the brain and the crew. Monthly only when we run it for you. USD and INR.

Brain + CrewAdvise mode

$59₹2,999one time

You paste. You get. You ship.

All sixteen agents plus the Brain Builder, installable in your own AI. Your tokens.

  • All sixteen agents in Advise mode
  • The Brain Builder: version 1 of your brain from your storefront and six answers
  • Runs inside your own ChatGPT or Claude, no credentials
  • Every output is copy, a list or a file you paste yourself
  • All five bonuses below
  • 12 months of agent updates

Best for: You want the brain and the crew today and do not mind pasting.

Opening soon, email us

HostedAutonomous mode

from$79₹4,999per agent per month

It runs. It sends. You read.

Autonomous. Our infrastructure, our tokens, weekly review. Bundles from four agents to the whole crew.

  • Agents run on their schedule without you starting them
  • Our infrastructure and our model tokens
  • Approvals over Telegram, weekly brief every Monday
  • Core Four at $249 a month, the whole crew at $549 a month
  • Free 14 day trial of Competitor Watch and Weekly Brain Update, no card
  • Founding price lock for the first 100 customers

Best for: You want it to run while you run the store.

Opening soon, email us See hosted pricing and the picker

Pay in USD or INR. The price is the same product either way. Payments are handled by Dodo Payments. You get the files and instructions by email after checkout.

Add-ons, priced under their tier.

Add them at checkout or later by email.

Brain + Crew

  • Brain Build$39₹2,999

    We build version 1 of your brain for you from your storefront, reviews and a short questionnaire, and hand you the file with an evidence map.

  • 40 ad creatives$59₹4,999

    A finished batch from the Ad Creative agent: contact sheet, files per format, four copy options per field, claims ledger and QA sheet.

  • Zero-Budget Video Ads course$19₹1,499

    A short course on making video ads for your products with zero ad budget.

Connected

  • Creator launch pack$99₹7,999

    Creator Outreach run for you: qualified list, drafted first emails, budget exposure, and the send batch queued for your approval.

  • 40 ad creatives$59₹4,999

    The same finished batch, uploaded paused to your Meta account so you activate with one tap.

  • Second store$59₹4,999

    A second brain and a second set of connections for another store you run.

Hosted

  • Custom agent buildTalk to us

    An agent for a job the sixteen do not cover, written to the same contract: brain reads, workflow, guardrails, approvals, write back. Email us

Five bonuses. Every tier.

Included with Brain + Crew, Connected and Hosted.

  • Market Playbooks

    Country by country: sale calendar, delivery expectations, COD and return behaviour. Your brain loads the one for your market.

  • 40 Ad Concept Templates

    The angle ladder Ad Creative uses: problem, mechanism, proof, offer, identity, comparison, honest urgency. Forty concepts to fill in.

  • The Skills Shelf

    A curated index of 60 open source skills with install commands. Credits every author. Redistributes nothing.

  • Weekly Operating Rhythm

    The seven day schedule the hosted crew runs on, as a checklist you can run yourself.

  • 12 months of agent updates

    Every agent file we improve for a year, included.

Founding price, locked for the first 100.

The first 100 Hosted customers keep their price for as long as they stay subscribed. That is the only urgency on this page. No countdown, no fake scarcity.

Hosted pricing will change as the crew grows. If you are in the first 100, yours will not.

100founding seats

Questions a careful owner asks.

I use ChatGPT already. What do I actually get in Brain + Crew?

Files. A Brain Builder agent that writes your brain from your storefront and six answers, sixteen agent files with their workflows and guardrails, the five bonuses, and instructions for loading them into ChatGPT or Claude. You paste the brain plus one agent, give it the input it asks for, and get its output contract back: a summary, then the files. Your tokens, your account, nothing connected.

What does Connected connect to?

Your tools on your own keys, in a 90 minute session with a person: a Shopify custom distribution app with named scopes, Meta Ads, your email tool, your mailbox for outreach, your review app. Every agent page lists exactly which tools it uses and in which mode. You can connect fewer.

How long does the first run take?

The Brain Builder needs your store URL, your country and six answers. Store Fix then runs on your store URL alone. Its first output is a weighted score with the count of checkpoints observed, the top five findings in one line each, and the fixes drafted in your voice.

Can I upgrade later?

Yes. The brain you build in Brain + Crew is the same file the Connected session refines and the Hosted crew runs on. Nothing is thrown away when you move up.

Will it change my store without asking me?

No. Every write to your store, every message to a customer or creator, and every rupee or dollar of spend needs an approval you tapped. The approval is a one use token that expires. No record means no action. Silence is never consent. Store Fix, for example, asks once for the whole batch, applies it to product content only, and records every previous value so you can revert.

Can it spend my ad budget on its own?

No. Ad Creative uploads every campaign, ad set and ad paused, then reads back the status and fails the upload if anything is not paused. Activating a campaign and setting a budget are separate approval gated actions. Ad Growth keeps new accounts in Advise for the first 14 days, never moves a budget more than 20 percent in a day, never breaches your daily cap, and pausing a loser is the only thing it does without asking, because pausing costs nothing.

What access does it need?

Level 1 needs nothing but your store URL: public catalogue, pages and reviews are enough for the brain and for Competitor Watch, Store Fix audits and Ad Creative drafts. Level 3 means you connect tools on your own keys: a Shopify custom distribution app with named scopes, Meta Ads, your email tool, your mailbox, your review app. Each agent page lists exactly which tools it uses and in which mode.

Does it email my customers or creators by itself?

First emails always pause for your approval, in every mode, including Autonomous. Creator and affiliate outreach sends only from your own connected mailbox, never from our domain, at most 20 first emails a day, and never a fourth message to a creator who stayed silent. There are no cold Instagram DMs. Ever. A private reply goes only to someone who commented on your post, once, within seven days.

Is this just ChatGPT with a long prompt?

The Brain + Crew tier does run inside your own ChatGPT or Claude, on your tokens, and we say so. What you are buying is the brain: a versioned document with six layers that every agent reads before it works and writes back to after. Plus sixteen agent contracts with workflows, quality gates and guardrails you can read on this site. Hosted adds the tools, the approvals over Telegram and the weekly schedule.

What is the brain, concretely?

A living, versioned document about one store. Six layers: identity, customers, products, competitors, performance, learnings. The Brain Builder writes version 1 from your storefront, your public reviews and six answers from you, and marks anything it inferred. Only the Weekly Brain Update may write performance. Learnings are append only, so nothing gets quietly rewritten.

Will it make up claims about my products?

It cannot. The brain holds claims_allowed, built only from text found on your own storefront, and claims_forbidden, built from your category's regulated claims. Every drafted line is checked against both. Anything that fails is rewritten or removed and listed as needs your confirmation. Ad Creative ships a claims ledger with every batch: every claim, its source, allowed or rewritten.

I am not on Shopify. Can I use it?

Yes, at level 1. Storefront only mode works for any store because the public catalogue and pages are enough for the brain, Competitor Watch, the Store Fix audit and Ad Creative drafts. Act mode writes to a store through Shopify GraphQL first. Other platforms come later and we will not pretend otherwise.

How do I undo something?

Store content changes ship with a changes file that holds every previous value, so a rollback is re applying the old value. Ads are created paused in a campaign named StoreCrew with the date, so you can see and pause everything the crew made. Flows are created disabled. Pages are created as drafts. You can pause any agent, and a hosted plan is monthly.

Where does my data live and who can see it?

Under your customer id. Every table carries it and every query filters by it. Competitor Watch never logs in, never submits a form, never adds to cart. Google review text is never stored. Secrets live in a secrets store, not in code or logs, and tokens are redacted from every log line.

Why do you not show ROAS or revenue numbers?

Because we would have to invent them. The site shows the mechanism and the price. Inside the product, the Weekly Brain Update reports revenue divided by spend and always labels it blended, never repeats platform reported ROAS, and writes likely because with evidence or no clear cause. Never a bare causal claim.

What is the founding price lock?

The first 100 Hosted customers keep the price they signed up at for as long as they stay subscribed. That is the only urgency device on this site. There is no countdown.

You paste. You get. You ship.

Stop being the whole marketing team.

Build the brain today. Put the crew on it. Keep the tap.

Founding price lock for the first 100 Hosted customers. No countdown.