How TCS built an agentic test orchestrator with Amazon Bedrock AgentCore
Tata Consultancy Services (TCS) built an agentic test orchestrator on Amazon Bedrock AgentCore that turns requirements into executable, governed tests for its Banking, Financial Services, and Insurance (BFSI) clients. Learn how specialized agents, per-tenant isolation, and workload-aware execution cut testing effort by 88% in an internal benchmark.
First seen by Oriel on .
AI summary
TCS built a multi-tenant agentic test orchestrator on AWS that turns project requirements into governed API and UI tests, reporting an 88 percent effort reduction in an internal benchmark.
- Specialized agents handle scenario design, Gherkin and Java or Python test generation, refinement, validation, and execution, with a deterministic supervisor routing tasks.
- Amazon Bedrock Knowledge Bases ground generation in tenant-, project-, and session-filtered requirements and source files; tenant planes also have separate identity, storage, keys, and knowledge bases.
- The execution agent routes API tests to AWS Fargate and Selenium UI tests to EC2-backed Amazon ECS, and uses a bounded LangGraph workflow for execution and controlled code-error fixes.
- In a benchmark of about 100 scenarios, effort fell from roughly 200 hours to about 24 hours; TCS notes that results vary by workload, application complexity, and team.
#agentic ai #software testing #amazon bedrock #aws
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 78fec7a3d16c37b034f25f58b80fa621d5222843 | https://aws.amazon.com/blogs/machine-learning/how-tcs-built-an-agentic-test-orchestrator-with-amazon-bedrock-agentcore/ Read discussion |