Know your best customers, and the ones slipping away.
Ask who your champions, new customers and at-risk customers are. Concierge scores every customer on how recently they ordered, how often and how much they spent, then names the groups with the rule behind each.
- scores on three measures
- 1 to 5
- scores on three measures
- customer groups with rules
- Named
- customer groups with rules
- groups cover every customer
- Adds up
- groups cover every customer
The problem
Lists built on gut feel miss people. RFM, short for recency, frequency and monetary value, scores every customer the same way, so you can see who is loyal, who is new and who used to buy often but has gone quiet.
What it reads.
Your orders
Each known customer's orders and net totals.
Recency
Days from a customer's last order to the end of the window.
Frequency and spend
How many orders and how much net revenue. Unknown totals are left out and counted.
Your group names
Default rules for champions, at risk, new and hibernating, or your own.
The steps it follows.
- 1
Measure each customer
Concierge prepares your orders on its own computer and measures recency, frequency and spend for every known customer.
- 2
Score 1 to 5
Each measure is scored by fifths of your customers, with ties split evenly, and the cut points are printed.
- 3
Name the groups
For example, champions score 4+ on recency and frequency; at risk score 2 or less on recency but 3+ on frequency.
- 4
Check the total
Each group's count and revenue, with proof the groups add up to all customers.
A worked example.
A made-up store, to show how the playbook works from question to answer.
- The store
- An apparel brand with seasonal drops and an email list it wants to target better.
- The question
- "Who are our at-risk customers right now, and how much have they spent with us?"
- What Concierge does
- Prepares orders for the window you set, measures each customer, scores the three measures 1 to 5 by fifths, and applies the group rules, starting with at risk (recency 2 or less, frequency 3 or more).
- What comes back
- A group table (champions, at risk, new, hibernating and the rest) with customer counts and revenue, the score cut points, the rules used, and a check that the groups cover every customer.
- How to read it
- At-risk customers have bought often but not lately, so they're worth a personal win-back. Champions are the people to ask for reviews or referrals. New customers need a reason to place a second order.
- A good next question
- "Give me the at-risk customers as a spreadsheet." Or ask what champions usually buy together with the product affinity playbook.
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: "Who are our at-risk customers right now, and how much have they spent with us?" 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 RFM segments 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.
Named groups
Champions, at risk, new, hibernating and the rest, with counts.
Revenue per group
How much each group has spent, so you know where the money is.
The rules shown
The exact scores and cut points, so your team can agree on them.
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
Who your best, loyal, new and at-risk customers are, based on how recently each customer ordered, how often, and how much they spent.
When you are planning a win-back, a VIP offer or a review request and need a list of the right customers with a rule you can explain.
Yes. Name them in your question, like "at risk means no order in 90 days and at least 3 orders", or edit the playbook so every answer uses them. The rule used is always printed.
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 RFM segments 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.
