# AI proposes. FutureBank governs. The bank executes.

Canonical: https://getfuturebank.com/trust
Last updated: 2026-10-06

Agentic banking lives or dies on trust. FutureBank never gives a language model unrestricted access to your core. Every request passes your controls, then executes deterministically and leaves a record.

[Talk to our team](https://getfuturebank.com/contact)

## Agentic at the interface. Deterministic at the core.

Your policies, permissions and limits govern every action. AI understands the intent. Your bank governs the execution.

- **Permission comes first.** Identity, customer consent and granular access define what an agent can see and do, before it does anything.
- **Execution has boundaries.** Bank-defined policies, limits and approval workflows govern every authorised banking action.
- **Every action leaves a record.** Audit and reporting show every request, decision and action flowing through your banking environment.

## Nothing reaches the core unchecked.

- **Identity**: Customers and employees authenticate through the bank's identity provider. KeyCloak is built in, and compliant OIDC providers are supported.
- **Agent authorization**: Every assistant or agent is registered, scoped to a customer or role, and can be revoked at any time.
- **Customer consent**: Granular, time-bound consent per assistant and per capability, visible to and revocable by the customer.
- **Capability permissions**: Each agent only discovers and calls the canonical capabilities it has been granted.
- **Beneficiary validation**: Payments resolve to saved, verified beneficiaries. New beneficiaries follow the bank's rules.
- **Transaction limits**: Limits per agent, per customer and per capability, separate from channel limits.
- **Policy**: Bank-defined rules evaluated deterministically. The model never decides policy.
- **Approval & step-up**: Customer approvals in the banking app. Maker-checker for employee actions where required.
- **Audit**: A complete trail of every request, decision and outcome, available to operations and compliance.
- **Execution**: FutureBank invokes the deterministic capability through the canonical model. The language model never talks to the core.

## Bank-grade underneath, not bolted on.

- **Fine-grained encryption**: End-to-end encryption that can be applied to individual features and data flows.
- **Identity built in**: KeyCloak ships with the platform and works alongside compliant OIDC providers.
- **Event-based observability**: An event-driven microservice architecture makes every interaction traceable.
- **Your environment**: Cloud or on-premise, managed or self-hosted. Data stays where you decide.

## Your bank. Your architecture. Your control.

Governance includes where FutureBank runs and what it connects to. Choose either side of every decision.

- Cloud or On-premise
- Managed or Self-hosted
- Existing core or New core
- FutureBank channels or Your own channels
- FutureBank partners or Your partners
- API-first or Agent-first

---

Start a conversation about what agentic banking could mean for your bank, beginning with one governed journey. [Let's connect](https://getfuturebank.com/contact) · [Play · Pilot · Build · Run](https://getfuturebank.com/get-started)