The One About Agents & Evals (Round II)
Join practitioners in Singapore for a deep dive into the challenges and realities of building, shipping, and evaluating AI agents for production. Speakers will share insights on iterating data agents, getting agents to production, and why conventional evaluations may not scale to real-world trust.
The One About Agents & Evals (Round II)
Join practitioners in Singapore for a deep dive into the challenges and realities of building, shipping, and evaluating AI agents for production. Speakers will share insights on iterating data agents, getting agents to production, and why conventional evaluations may not scale to real-world trust.
This event focuses on the practical challenges of developing and deploying AI agents into production environments. Practitioners will share their experiences with the development lifecycle, including common hurdles like failed iterations, debugging, and managing token costs. Attendees can expect discussions on strategies for moving agents beyond initial demos, methods for evaluating their readiness for real-world use, and insights into establishing trust in agentic AI systems, particularly in critical applications. The session is suitable for those involved in AI research, product development, and engineering.
Listed on Luma. Full details and registration on Luma
Summary AI-generated; content may not always be accurate.