Learn to build reliable and controllable planning agents in this conference talk from the AI Engineer World's Fair, where Yogendra Miraje from FactSet shares practical insights from developing real-world plan-and-execute agents. Discover how to maintain control over autonomous agents while preserving their flexibility through agentic workflows, blueprints, and evaluation techniques. Explore the challenges of making LLM-powered agents more predictable and reliable without sacrificing their autonomous capabilities. Gain actionable strategies for steering agent behavior, implementing robust control mechanisms, and ensuring your planning agents align with real-world user goals while maintaining safety and reliability in production environments.