quality_assurance · ecommerce · workflow
Amazon AMET Payments team reduces QA test case generation from 1 week to hours with SAARAM multi-agent AI
The AMET Payments QA team manually analyzed BRDs, design documents, UI mocks, and historical test preparations for each new feature, consuming 1 week per project and requiring one full-time engineer annually just for test case creation.
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 · Document routing at entry point
The file type decision agent serves as the system's entry point, categorizing and routing documentation files, Figma designs, and code repositories to appropriate downstream agents.
Tools used
Amazon BedrockClaude SonnetStrands Agents SDKPydanticAmazon Q Developer for CLIAmazon Bedrock AgentCoreAmazon CloudWatchMermaid
Outcome
SAARAM reduced test case generation from 1 week to hours, cut QA validation effort from 1.0 FTE to 0.2 FTE, identified 40% more edge cases than the manual process, and achieved 100% adherence to test case standards.
What failed first
Initial single-agent AI attempts fed entire BRDs to one agent and produced generic, non-actionable test outputs due to context length restrictions, lack of specialized processing phases, and hallucinations creating irrelevant test scenarios.
Results
Time saved1 week to mere hours
Volume1.0 FTE to 0.2 FTE
Grounding & classification
Source type: technical build writeup
35 fields verified against source quotes.
agentic workflowdata extractiondocument aimulti agent workflowpolicy documentbuilder submittedfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommercefinancial servicesaccuracy improvementcycle time reductionemployee productivitytime savedtechnical build writeupback office opsquality assuranceagentic task executionextract classify route