By 
Update, 25 September 2026: Miko Claude AI is now live on the Shopify App Store. The shipped app scores customers with RFM and rule-based logic inside the app itself, with no separate machine-learning service. Churn risk is a score from each customer's recency and usual gap between orders, lifetime value is their actual spend to date, and Claude writes segment email copy and the weekly report summary. We have corrected the architecture details below to match.
If you run a Shopify store and you ever clicked into Shopify Analytics, you have seen the same dashboards everyone else has. Total revenue. Conversion rate. Average order value. Maybe a top-products list. Useful information. None of it tells you what to do tomorrow morning.
The hard problem in commerce in 2026 is not measurement. It is action. With customer acquisition costs at all-time highs and acquisition channels (Meta, Google, TikTok) compressing margins year over year, every brand we work with has come to the same conclusion: the next dollar of revenue comes from a customer you already have. Not a new one.
That conclusion is uncontroversial. The hard part is operationalising it. Who, exactly, should you email this week? Which customer is most likely to churn in the next 30 days? Which one is silently about to become your top spender? Shopify Analytics will not tell you. Klaviyo will not tell you (it sends, it does not decide). Spreadsheets full of order exports get you 40% of the way there if you have a data analyst on staff.
That gap is exactly what Miko Claude AI exists to close.
What Miko Claude AI does, in one sentence
Miko Claude AI is a native Shopify app that reads your customer purchase history, segments customers with RFM scoring, predicts churn risk, tracks lifetime value, and surfaces specific actions for you to take to grow revenue.
That is the whole product in a sentence. The interesting part is how it does it, and why we believe it works better than the alternatives.
The five pieces, in order
1. Automatic RFM segmentation
RFM stands for Recency, Frequency, Monetary. It is the oldest, best-understood segmentation framework in retail. It works. It has been a quiet workhorse of CRM strategy for thirty years. Miko Claude AI computes RFM scores for every customer the moment you install, then keeps them fresh nightly. Every customer lands in one of ten segments: Champions, Loyal Customers, Potential Loyalists, Active Buyers, At Risk, Needs Attention, Lost, High Value, Average, and Low Engagement.
You have probably read about these on a marketing blog. The difference is that until now, computing them required a data team. Miko does it automatically.
2. Churn prediction
A churn-probability score (0 to 100) per customer. A rule-based score built from recency relative to the customer's own historical cadence: the further a customer drifts past twice their usual gap between orders, the higher the score. We update scores nightly so the moment a Champion starts looking like At Risk, you see it.
The point of the score is not to be perfect (no churn score is). It is to rank. If you have 5,000 customers and you can only realistically reach out to 100 this week, you want the right 100. Churn ranking turns that from guesswork into a list.
3. Customer Lifetime Value (CLV) tracking
Actual lifetime spend for every customer, tracked alongside their order pattern and recency. Paired with RFM and a VIP probability score, a new customer with two large orders stands out very differently from a new customer with two small ones even though both show "2 orders" on a basic dashboard.
Lifetime value and the miko-vip and miko-high-value tags let you find your top spenders and route them to a VIP onboarding sequence, automatically.
4. Rule-based segments (beyond RFM)
RFM scores every customer on the same three axes. Rule-based segments add plain behavioural rules on top. Miko Claude AI creates segments such as VIP, high value, at risk, lapsed, first-time, one-time and bulk buyers, and tags each customer to match. Patterns worth looking for in your own order history:
- Bulk reorder accounts: customers who order the same SKU at 3-4x typical volume on a quarterly cadence. Often hidden B2B accounts buying through your retail storefront. Tag them and route to a wholesale conversation.
- Discount hunters: customers whose entire order history sits behind promo codes. Different lifecycle from full-price customers, do not waste a re-engagement campaign on them.
- Single-product loyalists: customers who reorder the same one item for years and never explore the catalog. Different cross-sell strategy entirely.
Frequent reorderers land in the bulk buyer segment automatically. The others are worth checking by hand.
5. Claude-written outreach
Here is the part where we sound different from every other "AI" customer app on the App Store. We do not just hand you a dashboard of numbers and let you figure out what to do. Each segment comes with a plain-English playbook and a recommended action, and we use the Anthropic Claude API to write the win-back email for it.
So instead of seeing raw scores, you see something like: "These customers used to buy regularly but have gone quiet. Recommended action: send a personalized win-back email with a time-limited offer."
That is the difference between insight and action. The first is a status report. The second is an instruction.
What Miko Claude AI does not do
One thing we want to be explicit about: Miko Claude AI is not an email tool. It does not send messages, it does not run campaigns, it does not replace Klaviyo or Shopify Email or whatever you use.
Miko Claude AI is the brain. Your existing email tool is the sender. Miko writes its segments back into Shopify customer tags (with a miko- prefix so we never collide with your existing tags), and Klaviyo, Shopify Email, and Mailchimp pick those up automatically. There is no integration to set up.
This was a deliberate design choice. There are already excellent senders. There are very few good thinkers. We wanted to ship a thinker that plugs into the senders you already use, not a half-built sender that competes with them. If you want to read more about pairing Miko Claude AI with Klaviyo, the Klaviyo retention stack guide covers exactly that workflow.
Why we built it inside the Miko ecosystem
Miko Claude AI is the third app in a deliberate stack:
- Miko Loyalty and Rewards: turns customer behavior into retention via points, tiers, and rewards. Live on Shopify App Store.
- Miko B2B Wholesale Pricing: gives wholesale buyers a native experience with grouped pricing, NET terms, and merchant-side PO management. Live on Shopify App Store.
- Miko Claude AI: identifies which customers to focus on and what to do about them. In development.
Each app is useful on its own. The interesting math is what happens when you install all three. Miko Claude AI flags that a wholesale buyer is at high churn risk. Miko B2B surfaces that account in your dashboard with a flag. Miko Claude AI identifies a retail customer hitting Champion status. Miko Loyalty bumps them into the next VIP tier with a thank-you reward. One brain, three apps, compounding effect.
This is not a marketing slide. It is the actual architecture. The apps share the same customer-tag namespace and the same Tripster engineering standards. Install them together and they work together with no integration code from you.
The stack, for the technically curious
Miko Claude AI is built on:
- Built to feel like a native part of the Shopify admin. No separate dashboard to learn.
- PostgreSQL via Prisma for the application database.
- Remix (TypeScript) for the scoring itself. RFM scoring, churn-risk and VIP scores, and rule-based segments all run inside the app, with no separate ML service.
- BullMQ and Redis for background jobs. Scoring runs do not block the merchant UI.
- Anthropic Claude API for segment win-back email copy and the weekly report summary.
- Recharts for the in-app visualisations.
- Resend for the weekly merchant insight email.
Everything runs on Railway. Everything is observable. Everything degrades gracefully. Scoring runs inside the app itself, so there is no separate ML service to go down and you never see a blank dashboard.
When can I install it?
Soon. The core app, RFM scoring, Claude integration, and Shopify auth flow are all built and working in development. We are polishing the onboarding experience, hardening the data pipeline, and writing the documentation before we open a closed beta to a small group of Shopify merchants.
If you want to be on that list, join the waitlist. We will reach out the moment closed beta opens. Beta merchants get extended trial credits and locked-in launch pricing.
In the meantime, if you are already running manual churn analysis on your store, that gives you a useful baseline to compare once Miko Claude AI is live. The prediction article walks through RFM scoring by hand so you can see exactly what the app automates.
