Name the core abstraction and its failure modes.
OpenIBank Course
OpenIBank product architecture
How Hermon Finance, Maple AI OS, and OpenIBank can form a governed financial operating stack.
Learning Objectives
What this lesson should make precise
Translate the concept into a Maple/Hermon proposal contract.
Define at least one evaluation case that can fail the model safely.
Tutorial Flow
How this lesson becomes a demo and training target
Each tutorial is written as a user education path and a model-improvement artifact. The diagram shows how the idea moves into a lab, a typed contract, an eval gate, and then a Hermon/MapleAI demo route.
Concept
Product layers
Applied Lab
Applied lab: OpenIBank product architecture
Output Contract
product_layers, service_boundaries, model_routes, approval_gates
Eval Gate
Does the answer separate model proposal from deterministic execution?
Demo Route
OpenIBank training and public model checks
01
Product layers
OpenIBank should separate user experience, finance domain services, policy kernels, evidence stores, and model adapters.
- UI is not policy.
- Policy is deterministic.
- Model is advisory.
02
Service boundaries
Ledger, treasury, compliance, and notification systems should each expose narrow, audited interfaces. The model sees proposals, not raw unrestricted power.
- Narrow interfaces.
- Read-only model paths.
- Receipt every edge.
03
Commercial path
The niche is not generic financial chat. It is controlled operational intelligence for regulated workflows where evidence matters.
- Sell controls.
- Sell auditability.
- Sell safer automation.
Lab
Applied lab: OpenIBank product architecture
Sketch the OpenIBank architecture for treasury monitoring, reconciliation, AML triage, and audit-packet generation.
Expected result
- A typed JSON-style proposal rather than free-form advice.
- Clear authority boundaries and denied operations.
- A test or rubric that decides whether the proposal is deployable.
Evaluation
How Maple would grade this work
Rubric
- Does the answer expose assumptions instead of hiding them?
- Does the answer separate model proposal from deterministic execution?
- Does the answer produce artifacts that can be tested, reviewed, and rolled back?
Output contract
product_layers, service_boundaries, model_routes, approval_gates, audit_storeUse this lesson as training direction
A strong lesson gives users a mental model and gives Hermon a sharper target for examples, probes, and demo prompts.