> For the complete documentation index, see [llms.txt](https://docs.rainbird.ai/rainbird/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rainbird.ai/rainbird/getting-started/use-cases/customer-risk-rating.md). # Customer risk rating **Decision:** Banking — KYC & onboarding **Pattern:** Combined approach **Use case:** This solution rates a customer's risk and sets their due diligence level automatically wherever it has enough information to do so — and where it doesn't, it asks for the missing information rather than declining or guessing, so most cases require no human in the loop at all. See the [KYC / CDD Risk Rating & Perpetual KYC accelerator](https://rainbird.ai/accelerators/kyc-cdd-risk-rating) for a ready-built starting point. **End-user:** KYC analyst — only involved on the cases Rainbird can't complete without further information **The decision:** What risk rating and due diligence level applies to a customer, at onboarding and through perpetual KYC reviews. **The knowledge graph:** Encodes the bank's risk rating methodology and due diligence policy. **Integration:** Customer and case data feed into Rainbird automatically. Where everything needed for a rating is already present, Rainbird reaches its conclusion and the case proceeds straight through — no human involved. Where a specific fact is missing, such as a source of funds or a beneficial ownership detail, Rainbird asks for this additional information to be provided, rather than declining or making an assumption. That request can route to a KYC analyst's queue, or to an agentic system that can retrieve the answer directly from a registry or the customer. Once the fact is supplied, Rainbird resumes reasoning from where it left off and reaches its rating. **Evidence:** Every rating — whether reached straight through or after a follow-up request — returns the exact facts and rules that produced it, so the audit trail looks the same regardless of whether a human, an agent, or no one at all was involved along the way. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.rainbird.ai/rainbird/getting-started/use-cases/customer-risk-rating.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.