Technology
The Retention Ontology
The ontology is Swivel's model of your customer base: every customer, subscription, payment, and behavior represented as a connected object that your whole retention operation can reason over. It is kept live from the systems you already run.
Objects: the nouns
The ontology represents your retention world as typed objects. The core object types Swivel models out of the box:
| Object | What it represents |
|---|---|
| Customer | A single account or subscriber, with its full history. |
| Subscription | An active or past plan a customer holds. |
| Plan | A product/price tier a subscription can be on. |
| Payment | A billing event: successful, failed, or recovered. |
| Engagement Event | A unit of product usage or interaction. |
| Churn Risk | A customer's current, continuously updated risk state. |
| Cohort | A behavioral or lifecycle grouping of customers. |
| Lifecycle Stage | Where a customer sits in their journey (e.g. onboarding, established, declining, lapsed). |
| Intervention | A retention move made toward a customer. |
| Offer | A specific incentive that can be delivered in an intervention. |
Object set is configured to your business; the list above is the default starting model.
Properties: what each object knows
Every object carries properties kept current from your connected systems. A Customer carries tenure, current plan, lifetime value, lifecycle stage, and current churn risk. A Subscription carries status, renewal date, price, and discount history. A Payment carries amount, status, and retry history. Because these properties stay live, the System is reasoning over the present state of your business, not a stale extract.
Links: how objects relate
Objects are joined by typed links, the relationships that let the System reason across tools that don't normally talk to each other. A Customer holds a Subscription; a Subscription is billed by a Payment; an Intervention targets a Customer and delivers an Offer; a Customer belongs to a Cohort. These relationships are modeled once, so the System can answer questions that span systems without anyone stitching the data together by hand.
Why this matters
Right now, your customer data is fragmented. Legacy dashboards might flag a churn risk, but turning that insight into action requires your team to pull exports, stitch data together, and run plays manually. It's slow and expensive. Swivel's connected model changes that. It brings your data together so our agents can instantly turn insights into action, handling the heavy lifting and giving your team their time back.
Let the agents prove themselves on your accounts.
In three weeks, see the saves they worked, the reasoning behind each action, and what happened before you decide what comes next.