Summary
Full Transcript
Learn more: https://bit.ly/4mIpgcJ As generative AI applications grow more complex, spanning reasoning, retrieval, and tool use, writing and maintaining prompts across multiple components becomes challenging. Small changes to the model or input format can break your system, and debugging multi-step agents often requires guesswork. In DSPy: Build and Optimize Agentic Apps, a new short course taught by Chen Qian, co-lead of the DSPy framework at Databricks, you’ll learn how to build agents that are easier to reason about, debug, and improve over time. You’ll use DSPy’s signature-based programming model to define modular steps in your application, trace each component with MLflow, and improve performance using DSPy Optimizer without needing to hand-craft or re-tune prompts for every model change. Through hands-on examples like a sentiment classifier, a guessing game, a travel assistant, and a Wikipedia-based RAG agent, you’ll learn how to apply these ideas in practice. What you’ll learn includes: - Building agentic apps using DSPy modules like Predict, ChainOfThought, and React - Tracing and debugging multi-step workflows using MLflow - Improving accuracy through prompt tuning and few-shot example generation with DSPy Optimizer This course is ideal for developers and engineers looking to build more maintainable GenAI applications. No prior DSPy or MLflow experience needed. Enroll now: https://bit.ly/4mIpgcJ
Continue this lesson in the app
Install CourseHive on Android or iOS to keep learning while you move.
