Latest

Best practices for optimizing tool usage by LLMs and frameworks for evaluating the performance of agentic systems.

Techniques for improving the reliability of autonomous agents, including guardrails, self-reflection, and robust error handling.

An introduction to building agentic AI applications, focusing on the shift from basic prompt engineering to robust agent engineering.

A deep dive into Google Agent Development Kit (ADK): The framework for building, orchestrating, and deploying scalable multi-agent AI systems.

Reflecting on my journey from medical imaging and voice AI to leading LLM initiatives at Coinbase.