Amazon Finance Automation builds a generative AI Q&A chat assistant using Amazon Bedrock
AP and AR analysts in Amazon Finance Operations spent hours to days answering customer queries, requiring time-consuming back-and-forth with subject matter experts and review of multiple policy documents, with new hires especially lacking immediate access to necessary information.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Customer query submitted
AP and AR analysts receive queries from customers through email, cases, internal tools, or phone.
Tools used
Amazon BedrockQUILL EditorAmazon Titan Text Embeddings G1bge-base-en-v1.5all-mpnet-base-v2
Outcome
Through iterative improvements in document segmentation, prompt engineering, and embedding models, the team improved RAG accuracy from 49% to 86%, drastically reducing the time required to address customer queries.
What failed first
The initial RAG-based chat assistant achieved only 49% response accuracy—far below expectations—due to incomplete contexts from fixed-chunk segmentation, LLM hallucinations when no relevant context was retrieved, and responses that were too brief to be useful.