New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy... framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here:show more

@databricks 👋

In this free Substack post I share code for several machine learning models and engage in hyperparameter tuning that yields a model that delivers superior returns in the Gold market.

@databricks sounds like an exciting opportunity to dive into the world of genai applications.

Finally. No more spending hours handcrafting brittle prompt chains. Agentic workflows demand robustness, adaptability, and clarity — DSPy delivers. It’s not just about auto-tuning prompts — it’s about letting your LLM systems learn how to optimize themselves. Pairing DSPy with MLflow for traceability and performance visibility? That’s the missing layer GenAI builders have been waiting for. If you’re serious about LLM-based systems, take this course. Your future self (and your agents) will thank you.

@databricks Wow dspy and mlflow. This will be an very very good course. Will work trough it during the weekend.

@databricks Awesome! Can't wait to work it through. I think you're doing so much good by releasing all of these short courses. It's like a goldmine

@databricks right on time

I think this is a long time coming. @DSPyOSS has a reputation for being "advanced" but it's everything BUT that. It actually simplifies the most complex concepts into simple primitives without losing flexibility. In fact it increases flexibility. IMO it's the simplest and easiest way to build complex AI applications for ANY workflow. Vibe coders especially need to take notice. DSPy is the tool they were looking for...

@databricks DSPy's here to save us from prompt-tuning marathons! 🚀 Who knew AI could be this lazy—and smart? Sign up, level up, and let's make those LLMs work for us, not the other way around!

@databricks DSPy is pretty awesome, it’s a huge vote of confidence that Andrew himself is making a course on it. Also just going to respectfully plug my stuff here. I too made a video recently explaining DSPy through 8 short project tutorials.

@databricks woahhh