Building Secure-by-Design AI Agents at Scale

Shlomy Cohen ו-Sefi Avrech, Sr. Solutions Architects, AWS | Melih Bahar, AI/ML & Engineering Lead, Dream

AWS Summit Tel Aviv 2026 · AWS AI Cloud Ops, Infrastructure & Security · 41 min · 17 pages

AI agents represent the next evolution of AI, capable of using tools through adaptable workflows with a high degree of autonomy. These advanced capabilities, however, introduce new security challenges and attack vectors. In this session, we explore the emerging risks - including those outlined in the OWASP Top 10 for Agentic Applications, and learn how to utilize threat modeling, defense strategies, and AWS security capabilities to architect secure-by-design agentic applications at scale. We will be joined in this session by AWS customer Dream, who will share their experience building production-grade agentic applications.

Generated automatically from the recording's transcript. It's meant to replace re-watching, not the recording itself — verify against the video at the timestamp before quoting formally. Slides belong to the speakers and organisers. Produced with recording-to-pdf.