Servicing Plane overview
The servicing control plane is the operating layer for loan and merchant-advance servicing — coordinating cases, work, compliance, people, and the named AI workforce natively on the LendEasy Lending Core, across 228 implemented operations.
The servicing control plane is where the operational work of servicing happens. It coordinates cases, tasks, and channels across your human agents and the named AI workforce — Nova, Cookie, Docgest, and Arya — applies current-fact policy at owning borrower-contact and governed-operation boundaries, and drives each matter to an outcome. It runs natively on the LendEasy Lending Core, a system of record the plane observes and governs but deliberately does not own — and, as an additional deployment option, the same workflows can run on a core you already operate. Consumer installment, BNPL, and merchant-advance servicing run on the same model.
The runtime today
The composed platform exposes 228 servicing operations, measured from the route manifest of the current build — 29 case operations, Nova’s full 16-operation voice contract, the 13-operation workflow builder, 8 scheduled-callback operations that hold a phone promise as a first-class task, and audited evidence exports among them — of 426 operations documented across the whole contract. See API availability for the exact current boundary; the API reference badges current routes and retains roadmap contracts beside them.
A control plane, not a CRM
A CRM records what happened. The servicing control plane tracks the outcome you are trying to reach: it holds the operational state you want, submits approved requests to the system of record, verifies the core actually reached that state, and creates work when reality does not match. Divergence surfaces as drift and becomes prioritized work — never hidden behind a completed task.
Who owns what
The split is deliberate and never blurred. The system of record — natively, the LendEasy Lending Core — owns financial truth; the servicing plane owns the operational work around it. (An existing core can also fill this role: see Bring your own system of record.)
| The system of record owns | The servicing plane owns |
|---|---|
| Balances and repayment schedules | Cases, tasks, and queues |
| Payment allocation and transactions | Interactions across phone, email, and chat |
| Accounting and delinquency calculation | Compliance decisions and approvals |
| Charge-off, payoff, and reversal | Action-request lifecycle and evidence |
| Autopay and restriction facts | Promises, AI governance, and audit |
How work moves
A case is opened from a signal or by hand and carries the matter to closure. Work reaches an eligible worker — human or AI, both registered in the same workforce — through smart queues. Before a borrower contact or governed account change executes, the owning operation invokes the compliance engine with current facts.
When policy yields one safe allowed result, the typed operation executes immediately. An action request exists only for an explicitly approval-required, deferred, manual, external, or unavailable boundary. Where the workflow itself acts, it does so through a typed case effect rather than an arbitrary command. A case supplies causation and scope; it never grants the operation permission or fabricates maker-checker. Every decision, approval, effect, and override lands in the evidence graph.
Automation comes in two forms
The plane draws a hard line between two kinds of automation. Deterministic, policy-gated automation — reminders, notices, and routing — is templated and rule-bound, and each instance still passes a per-recipient compliance check. AI autonomy is different: an agent exercises judgment, bounded by its work packet and the autonomy ladder. You can run substantial deterministic automation well before AI autonomy rises.
Explore the servicing guides
- Meet the agents — Nova, Cookie, Docgest, and Arya: the named AI roster and what each one works.
- Case model & lifecycle — how a matter is modeled, tracked, and closed.
- Smart queues & routing — how work reaches the right worker.
- Workforce & worker registration — provisioning humans and registering AI workers.
- Compliance engine — the decision gate in front of every contact and action.
- AI agent workforce — the contract every agent works under.
- API availability — the exact runtime surface and its boundary from roadmap contracts.
- Governed operations & action requests — the eight case-scoped operations and the approval lifecycle.
- Case effects — what workflow automation committed to, and how a failure is recovered.
- Case notes — revisioned operational commentary with links, archive, and redaction.
- Servicing reports — bounded operating projections and the curated investor pack.
- Reconciliation & drift — keeping operational and authoritative state in agreement.