What changed

Tata Consultancy Services (TCS) created an agentic test orchestrator using Amazon Bedrock AgentCore to streamline testing for Banking, Financial Services, and Insurance (BFSI) clients. The platform automates test scenario generation, execution, and reporting, reducing the need for repetitive manual work by quality engineers.

What this means in practice

TCS identified four key requirements for its BFSI clients: test scenarios must be grounded in project-specific context, support both API and browser-based UI testing, ensure tenant data isolation, and provide a repeatable path from requirement ingestion to test evidence and reporting. The agentic test orchestrator addresses these by decomposing testing into specialized tasks, each handled by its own agent with specific tools, validation rules, and context. Amazon Bedrock AgentCore enables TCS to scale these agents across multiple tenants while maintaining isolation through session-level microVMs. The platform integrates with Jira, GitLab, and other tools to ingest requirements, generate tests, and execute them on Amazon ECS, storing results in Amazon S3 and DynamoDB.

Limitations and availability

The solution is a multi-tenant SaaS platform built on AWS, with tenant onboarding handled through an administrative API and AWS CodeBuild. Each tenant receives its own Kubernetes namespace, Amazon Cognito user pool, AWS KMS key, and Amazon Bed, ensuring data and identity isolation. The platform is designed for BFSI clients and is available as a service through AWS, though the exact availability and deployment timeline are not specified in the announcement.

Source facts for TCS built agentic test orchestrator using Amazon Bedrock AgentCore: BFSI clients need to increase testing throughput while preserving the controls expected in financial services. The objective wasn’t to replace quality engineers. These industry needs generated four specific requirements for TCS.
Original AINewsTrend explainer based on the cited source. This graphic summarizes source statements; it is not an independent benchmark.

Sources and further reading

  1. awsml: How TCS built an agentic test orchestrator with Amazon Bedrock AgentCore