> 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.md). # Example use cases Get inspired with examples of Rainbird-powered solutions Every example below shows a different way Rainbird gets integrated. Look for whichever you recognise first — your **decision** ("I need something like our claims process") or your **integration pattern** ("I need something that works like an agent tool call"). Every example is tagged with both.
Use caseDecision domainIntegration pattern
Digital tax consultantTax & AuditGuided conversation
Real-time fraud claim decisioningInsurance — Claims fraudAutomated pipeline
Trade finance document compliance checkBanking — Trade financeDocument check
Mortgage decisioning for an AI lending agentBanking — Mortgage underwritingAI agent decision layer
Customer risk ratingKYC & OnboardingCombined approach
### Integration patterns * **Guided conversation** — Rainbird asks an end-user or advisor clarifying questions, one at a time, adapting each question to what's already been answered, and delivers a reasoned outcome at the end. Whether that end-user is an advisor talking to a customer, or the customer themselves, the pattern is the same. * **Automated pipeline** *(also called straight-through processing)* — Rainbird is called system-to-system, with no one seeing a UI. Data goes in, a decision comes back, and it flows straight into the next system. * **Document check** — Data already extracted from a document (by your own OCR/IDP pipeline) is checked against rules held in a knowledge graph, returning a pass/fail with an explanation for each check. Rainbird checks structured data, not raw documents. * **AI agent decision layer** — An AI agent calls Rainbird mid-workflow, over MCP or API, whenever it hits a decision that needs to be consistent and defensible. The agent handles the conversation and context; Rainbird handles the judgement call. * **Combined approach** — Most real implementations blend two or more of the above. The most common blend: an automated pipeline handles the clear-cut cases straight through, and asks for additional information where required to reach a conclusion, escalating to a AI agent or guided conversation with a human reviewer to capture this data. Don't see your decision here? The [accelerator library](https://rainbird.ai/accelerators) has 23+ working knowledge graphs across banking, insurance, tax and healthcare — a closer match may already exist as a starting point. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.rainbird.ai/rainbird/getting-started/use-cases.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.