ecommerce_ops · ecommerce · workflow
Rufus scales conversational shopping for 250M+ Amazon customers using Amazon Bedrock
Rufus was initially built on a custom in-house LLM optimized for the shopping domain, but training iterations took weeks or months, making it impossible to rapidly adopt advanced reasoning and larger context window capabilities as frontier models evolved.
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 shopping query
A customer asks Rufus a factual product question or shopping recommendation.
Tools used
Amazon BedrockAmazon NovaClaude SonnetAmazon Nova Web Groundingprompt cachingLLM-as-a-judgeconverse API
Outcome
Adopting Amazon Bedrock increased development velocity by over 6x. Rufus now serves more than 250 million annual users, with monthly users up 140% YoY and interactions up 210% YoY. Customers using Rufus are 60% more likely to complete a purchase, and auto-buy users save an average of 20% per purchase.
What failed first
Off-the-shelf models evaluated before the custom LLM performed poorly in shopping domain evaluations, and larger third-party models added unacceptable latency and cost penalties.
Results
Time saved140% YoY
VolumeMore than 250 million
Grounding & classification
Source type: technical build writeup
40 fields verified against source quotes.
agentic workflowai agentconversational aipersonalizationragrecommendation systemknowledge baseproduct catalogfailure mode describedmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedecommerceretailaccuracy improvementconversion increasecost reductionemployee productivitythroughput increasetechnical build writeupcustomer supportecommerce opsagentic task executionrag answering