Loading
Financial services · use case
A policy, not a promise: requests carrying account or customer data are pinned to the model you run yourself, statements and extractions go to a mid-tier model, and a hash-chained audit trail records why each request went where - with budgets per team enforced before a call is made.
Free plan, no card. Self-hosting is free forever; the rules below run the same way on both.
The situation
A bank's AI traffic mixes public questions with requests that carry account numbers, balances and names. Model risk, data residency and the regulator all ask the same thing - where did this request go, and why - and an application-level setting cannot answer it.
What changes
One request
Requests with account data pin to your on-prem model; the audit trail satisfies the regulator.
The policy
This is the rules.yaml that produces the behaviour above; targets.yaml names the models, agents and people it refers to. pin restricts the candidates instead of nudging them; the hash-chained audit records why.
rules:
- name: account-data-stays-onprem
when:
domains: [finance]
contains_pii: true
prefer: [llm-onprem]
pin: true
- name: statements-are-extraction
when:
domains: [finance]
actions: [extract]
prefer: [llm-mid]
weight: 0.6Example: Illustrative configuration or synthetic data, not a customer's.A reference configuration to start from - rules the router enforces as written, not a description of how a named customer runs it.
OpenSmartRoute is open source and the free plan keeps the full trace of every decision. Create a workspace, paste the rules, route a request.
Free plan, no card. Fifteen thousand decisions a month with the full trace.