NTT Develops AI Tools for Maintaining Existing Software

Oct 23, 2026
NTT developed technology that maps relationships among software documents, code and tests, detects inconsistencies, and generates tests for missing coverage.

NTT said in a press release it developed technology that prepares existing software assets for use by generative AI. The technology maps relationships among specifications, design documents, code and tests, then detects inconsistencies and missing information.

A separate test generation system identifies gaps involving abnormal conditions, boundary values, combinations of conditions and interactions among functions. It then generates executable tests to cover those gaps while retaining existing test assets.

In a preliminary experiment containing 41 intentional errors, NTT's traceability method detected 33 errors, or 80%, compared with 11 errors, or 27%, for retrieval augmented generation. In another test with six intentional bugs, the technology detected four and found three additional latent bugs.

NTT will evaluate the technology with software systems of different sizes, add support for more programming languages and artifacts, and use it in software development and maintenance projects.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.