See which products sell together, and what to offer next.
Ask which products or collections land in the same order. Concierge counts every pair, measures how much more often they're bought together than chance would give, and shows only pairs with enough orders behind them.
- of products or collections
- Pairs
- of products or collections
- together versus by chance
- Lift
- together versus by chance
- orders per pair by default
- 5+
- orders per pair by default
The problem
Bundles and add-on offers often start as a hunch. Real baskets tell you which pairs customers already choose, which offer is worth testing, and which "obvious" pairing barely happens.
What it reads.
Order lines
Every product line in every order.
Product titles
Your catalog, so pairs come back with names, not codes.
Collections
Your Shopify collections, when you ask about groups like cleansers and moisturizers.
A minimum
Only pairs seen in at least 5 orders, or the minimum you set.
The steps it follows.
- 1
Prepare the data
Concierge prepares a private copy of your order lines, products and collections and opens it on its own computer.
- 2
Keep known products
Lines without a known product are set aside and counted; products map to collections when you ask about groups.
- 3
Score every pair
Orders with both, how often B follows A, and lift: how much more often they appear together than chance would give.
- 4
Keep the solid ones
The top pairs with order counts, the minimum used and how many orders it looked at.
A worked example.
A made-up store, to show how the playbook works from question to answer.
- The store
- A beauty brand with about forty products in six Shopify collections.
- The question
- "Which collections are bought together most, and what should we offer after someone buys a cleanser?"
- What Concierge does
- Prepares order lines, product titles and collections, maps each line to its collections, then scores every pair of collections that appear in the same order.
- What comes back
- The top collection pairs with how many orders contain both, how often the second follows the first, and lift, limited to pairs in at least 5 orders. Then the pairs that start with cleansers, ranked.
- How to read it
- High lift with plenty of orders is the strongest signal. High lift on few orders is a lead to watch, not a sure thing. Two bestsellers can show up together often with lift near 1, which only means they're both popular.
- A good next question
- "Same thing for products, with a minimum of 20 orders." Then try the top pair as a bundle or an offer after checkout.
This store is invented for illustration. It is not a Chargezen customer, and no results are shown: your answer depends on your own data.
Run it, then make it yours.
You don't need to name the playbook. Concierge reads each playbook's "When to use" line and opens the one that fits your question.
- In the Chargezen admin
- Type your question in Ask Concierge, for example: "Which collections are bought together most, and what should we offer after someone buys a cleanser?" Concierge does the work and replies with the answer and any files.
- In ChatGPT or Claude
- Connect Chargezen to ChatGPT or Claude, then ask Concierge from the chat. The request goes to your workspace's own agent, with the same playbooks, and the reply comes back to the chat.
- In the Finn app for iPhone
- Type or dictate the question in the chat box on Home and send it to your agent. It's the same agent with the same playbooks.
- Change the steps
- Open Concierge > Build > Playbooks, pick Product affinity and baskets and edit the instructions. Edits apply to new requests; work already under way keeps the version it started with.
- Use your definitions
- If you've saved a definition for a term the playbook uses, like what counts as an active customer, Concierge applies yours instead and prints it in the answer.
- Choose who uses it
- It starts switched on for your workspace's operator agents that can analyze store data. Switch it on for other agents under Agents, archive it, or click New Playbook to write your own.
What you get back.
Top pairs
The product or collection pairs bought together most, with order counts.
Lift, explained
Pairs bought together more than chance, not just two bestsellers.
Thin pairs filtered
No conclusions drawn from a handful of orders.
Get answers you can check, without the spreadsheet afternoon.
Every Concierge workspace starts with these playbooks. Ask a question in plain English and see the numbers and the work behind them.
Common questions
Which products or collections are bought together, which pairs make good cross-sell candidates, and what a typical basket holds.
When you are building bundles, choosing an add-on or post-purchase offer, or arranging product recommendations.
Lift compares how often two items are bought together with how often you would expect if customers chose them independently. Above 1 means they go together more than chance; near 1 means they are just both popular.
No. Concierge sees the title and "When to use" line of every published playbook switched on for the agent, and opens the full steps only when one fits your question. You can still say "use the Product affinity and baskets playbook" to be sure.
Yes. It's your workspace's playbook: edit the steps, rename it, switch it on for other agents, archive it or delete it under Concierge > Build > Playbooks. A deleted default playbook stays deleted.
Running a playbook is a Concierge job, so it uses your workspace credits like any other job when Concierge runs on Chargezen-managed AI models. Concierge Starter is $20 a month with 20,000 credits. Pro is $199 a month with 199,000 credits, or $1,990 a year.
More playbooks and guides.
