Rethinking Pre-Training for Agentic AI
Episode · Dec 17, 2025
The TWIML AI Podcast
We use cookies for analytics.
Alexandre Pesant discusses the capabilities and limits of coding agents and development through natural-language intent. Topics include context engineering, changes between workflow-based and agentic architectures, scaling challenges, evaluations and interface design. The conversation examines how model improvements influence practical software-development tools.