Building Once, Running Everywhere: The Future of Portable AI Applications
AI is rapidly moving beyond the cloud — onto laptops, phones, browsers, vehicles, and edge devices. But for developers and testers, this creates a new challenge: how do you build, validate, and optimize an AI application once, then confidently run it across an increasingly diverse world of hardware?
This session explores the emerging era of portable AI applications, where models and applications can move seamlessly across CPUs, GPUs, NPUs, and other accelerators without requiring developers to reinvent their software for every target.
We’ll look at the technologies making this possible — from portable AI runtimes and hardware abstraction to intelligent compilation and automated testing — and the new challenges they introduce for performance, consistency, accuracy, and quality assurance.
Most importantly, we’ll explore what “build once, run everywhere” really means for AI developers and testers, and how portable AI could fundamentally change the way we build, test, and ship the next generation of intelligent applications.
About the speaker
Prashant Sharma:
Prashant is the Head of Developer Relations at Arm, where he leads the global mission to make Arm the platform of choice for developers building the next generation of computing — from AI at the edge and intelligent devices to cloud and emerging compute experiences. At Arm, Prashant works at the intersection of technology, developers, and ecosystems — building strategic partnerships, enabling early adopters, and creating programs that accelerate developer adoption at scale. Over his career, he has held leadership roles at Microsoft, Wix, and Qualcomm, building and scaling developer, community, and startup ecosystems around emerging technology platforms. Beyond Arm, Prashant is a Venture Partner at Mindset Ventures and an active advisor and seed investor, working with early-stage founders at the intersection of technology, product, and ecosystem growth. He lives in Seattle, where outside of technology he can usually be found exploring the expansive wilderness of the Pacific Northwest, buried in a good book, or discovering his next favorite wine.
About
TestMu Conf
Testμ (TestMu) is the world’s largest virtual conference on agentic engineering and quality, built by the community, for the community. As AI reshapes how we build, test, and ship software, Testμ Conf is where you connect, grow, and lead: agentic workflows, autonomous quality, battle-tested AI playbooks, hands-on workshops, and the engineering culture driving it all.
More Sessions
Join the builders, testers, and innovators shaping the next generation of web experiences.
Testμ Conf 2026 is where they meet.
