Video by Open Data Science and AI Conference via YouTube
Multi-agent systems promise autonomous workflows, specialized agents, and major productivity gains—but production reality is more complicated.
In this ODSC AI East 2026 session, Sinan Ozdemir, Founder of Crucible and AI & LLM Advisor at Tola Capital, explores the case for and against harnessing multi-agent systems. Drawing on enterprise deployments, his book Building Agentic AI, and real-world lessons from agent failures, Sinan breaks down why autonomy alone is not enough.
The session examines how teams can balance agent freedom with architectural constraints, evaluation loops, cost controls, human-in-the-loop gates, and progressive autonomy. Watch to learn how to decide how much “harness” your agents need and how to build multi-agent systems that deliver value without becoming systems you have to babysit.
————————————————————————————————————-
Visit our website and choose the nearest ODSC event to attend and experience all our training and workshops: https://odsc.ai
To watch more videos like this, visit https://aiplus.training
Sign up for the newsletter to stay up to date with the latest trends in data science: https://opendatascience.com/newsletter/
Follow us online!
• Facebook: https://www.facebook.com/OPENDATASCI
• Instagram: https://www.instagram.com/odsc/
• Blog: https://opendatascience.com/
• LinkedIn: https://www.linkedin.com/company/open-data-science/
• X (twitter): https://x.com/_odsc