Oscilar's September product update introduces an AI Workflow Copilot that builds and queries risk rules from plain English prompts, alongside workflow testing that adds single rule testing, backtesting against historical data and a clear diff view before a change goes live. The release also ships version 2.1 of its AML alert scoring model, a 50 percent improvement in P99 latency, and nine new integrations.
Our readThe copilot writes the rule, but backtesting and the diff view are what let a risk team ship it without a change control argument, because a rule change with a measured historical effect and a visible diff is a rule change with an audit trail. The AML scoring model version is worth logging on its own: a bumped model version is exactly the disclosure model risk teams ask vendors for and rarely get.