Certificerbar agentbaseret AI til debugging-analyse af embedded systemer

Med introduktionen af winIDEA AI Kit bringer TASKING certificerbar agentbaseret AI til debugging-analyse af embedded systemer (in english).

TASKING, a global leader in high-performance embedded software development tools, has launched the winIDEA AI Kit. This set of tools and files allows artificial intelligent (AI) agents to integrate with TASKING’s unified toolchain through the winIDEA development environment. 

Accessibility to AI agents within the development toolchain enables developers to automate multiple development workflows, accelerating software design and verification while maintaining strict requirements traceability to facilitate and simplify certification.

Embedded teams, especially those developing complex, multicore applications across automotive, aerospace and defense, industrial, medical, and robotics, face the challenge of delivering increasingly complex, functionally safe software under tighter development timelines. 

While AI can be used to help write, test, and verify software, requirements traceability requires developers take full responsibility for all AI activity. 

TASKING integrates AI into software workflows and provides context to generically trained LLMs on how code/scripts should be generated to improve developer productivity while maintaining the requirements traceability needed for certification to industry standards. 

Guardrails define what AI can do, while human oversight ensures accountability by enabling AI to support the development lifecycle without compromising reliability, functional safety or security.