TCS says AI testing workflow cut engineer effort by 88 percent in internal benchmark

Image: Primary

Published Tuesday, November 10, 2026 · 12:09 PM EST

Tata Consultancy Services says its AI testing system, running in production for banking, financial services and insurance clients, reduced engineer effort by 88 percent in a controlled internal benchmark across approximately 100 scenarios. The system turns project requirements into test scenarios and executable Java or Python tests, runs them and records results. Specialized agents use project-specific context, while separate tenant data stores and keys isolate clients. Quality engineers review and govern the generated work. The comparison measured design, scripting and execution effort against TCS's existing process. Results vary with workload, application complexity and team.

Sources

AWS Machine Learning Blog

Published by Tech & Business, a media brand covering technology and business. This story was sourced from AWS Machine Learning Blog and reviewed by the T&B editorial agent team.

Back to Newswire

Keep reading

Full wire

Robotics Capital

Path Robotics raises $300 million at $2.45 billion valuation

Path Robotics has secured $300 million in new financing, Bloomberg reported. The funding nearly quadruples the startup's valuation to $2.45 billion.

Capital

Clara raises $105 million for hiring and market expansion

Clara, a São Paulo-based startup that manages corporate spending, raised $105 million, Bloomberg reported.

AI Capital

Sparxity closes Series A, bringing total funding to $90M

Dresden AI chipmaker Sparxity has closed a Series A round led by ICM HPQC Fund, bringing its total funding to $90M, The Next Web reported. The company did not disclose the size of the round. Participants included Lockheed Martin Ventures, GlobalFoundries and the EIC Fund.

Security

Git releases fixes for six vulnerabilities, including recursive-clone code execution

The Git project released patches for six security vulnerabilities, including a flaw that can execute attacker-controlled code when a user recursively clones a malicious repository, GitHub announced. Fixes are available in Git 2.56.1 and six maintenance releases.

AI Capital

Ancep raises $8.5M to automate insurance brokers' administrative work

London-based Ancep has raised $8.5M in a round led by Creandum, with Kleiner Perkins and Vicus Ventures participating. The company will use the funding to expand and hire staff for its business developing AI agents for commercial insurance brokers.

Google opens Gemini 4 Carbon to paying API users and Ultra subscribers

Google made Gemini 4 Carbon available to paying developers and enterprises through its API, with a rollout also starting for Google AI Ultra subscribers. Introductory API pricing is $2 per million input tokens and $10 per million output tokens, matching Gemini 4 Argon.