Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Discover how to make data-driven decisions when selecting large language models for AI agent development in this conference talk from the Agents in Production 2025 event. Learn from a comprehensive study that evaluates 15 leading LLMs on real-world code summarization tasks, focusing on practical metrics essential for agent performance including verbosity, latency, cost, human-aligned accuracy, and information gain. Explore the critical importance of LLM selection as the foundation for building effective AI agents, moving beyond marketing hype and benchmark scores to understand actual performance in production environments. Gain actionable insights for choosing the optimal model for your specific agent use cases, whether you're developing autonomous coding assistants, developer-focused copilots, or multi-modal agent systems. Understand how proper LLM selection directly impacts agent capabilities in code understanding tasks, with practical guidance for evaluating models based on real-world performance rather than theoretical benchmarks.
