Recorded live during the Lightning Talks at the MLOps World | GenAI Summit 2025 — Austin, TX (October 8, 2025) Session Title: Purpose-Built Data Agents: This Is the Way Speaker: Josh Goldstein, Solutions Architect, Weaviate Talk Track: Agents in Production Abstract: As enterprises move from AI experimentation to large-scale deployment, context engineering has become the real differentiator between agents that work and those that don’t. Unlike simple prompt tuning, context engineering requires precision: giving AI systems exactly the right amount of information—no more, no less—to maximize performance and efficiency. In this lightning talk, Josh Goldstein, Solutions Architect at Weaviate, explains why purpose-built data agents are the key to mastering this balance. These agents automate the hard work of managing memory, knowledge retrieval, and contextual assembly, turning static LLMs into dynamic, responsive systems. Through real-world examples, Josh shows how teams are using data agents to accelerate time-to-value, reduce costs, and build reliable production-ready AI systems that understand and reason over their data. What you’ll learn: • The evolution from prompt engineering to context engineering • How purpose-built agents manage memory and knowledge efficiently • Real-world examples of data agents improving AI system performance • How automated context assembly drives accuracy and scalability • Why context engineering is the foundation of production-ready AI.