Evaluate Your Agent Skills: Build Evals That Actually Work

Shrey Shah is a Senior AI Software Development Engineer at Microsoft specializing in AI agents and harness engineering. He works on Azure core infrastructure, focusing on autonomous coding agents, with experience across AI agent development, RAG systems, local AI deployments, and generative AI tooling.

With a background in software testing, test architecture, and AI development, Shrey takes an evaluation-driven approach to building reliable AI systems. He also shares practical insights on AI engineering and agents with more than 20,000 followers on LinkedIn, helping developers move beyond AI demos toward reliable, production-ready systems.

Aki Wijesundara is an AI leader with a PhD in Machine Learning and extensive experience mentoring startups at Google’s AI Accelerator. With a career spanning both research and applied AI, Aki has taught 5,000+ students worldwide how to design and deploy production-ready AI systems.

He has worked across cutting-edge areas of applied AI, from LangChain and RAG pipelines to observability and large-scale deployment. As a researcher and educator, Aki bridges the gap between theory and practice, making complex systems approachable and actionable for engineers, founders, and product leaders.

Aki is also a frequent speaker and advisor to organizations adopting AI, helping them transition from experimentation to production at scale.