Building better LLM evals? Ben Wilson highlights how frameworks like #DSPy boost judge prompts—and reliability—as models evolve.
Tips for judge reproducibility/reliability: use reproducible pipelines, re-tune logic as endpoints change, & standardize. ✅
🎥 Watch more: www.youtube.com/live/HTxpmnO...
If, like me, you weren’t familiar with #DSPy, this was a great talk given at the Databricks Data & AI summit to walk you through why you should care.
If you’re writing prompts by hand in your apps, stop now and read this article by @dbreunig […]
Fun article on #dspy and #databricks being integrated into Jetblue’s tech stack #ttb
tastytechbytes.com/databricks-d...
written version with of talk at the 2025 Data and AI Summit by
#DrewBreunig lots of helpful links and diagrams on the use of #dspy for #promptoptimization he uses #chatgpt 4 and a smaller #qwen model www.dbreunig.com/2025/06/10/l... #databricks
www.dbreunig.com/2025/06/10/l...
Let the LLM Write the Prompts: An Intro to DSPy in Compound Al Pipelines Let the LLM Write the Prompts: An Intro to DSPy in Compound Al Pipelines I've had trouble getting my head around DSPy in...
#geospatial #gis #ai #prompt-engineering #generative-ai […]
[Original post on simonwillison.net]
Let the LLM Write the Prompts: An Intro to DSPy in Compound Al Pipelines Let the LLM Write the Prompts: An Intro to DSPy in Compound Al Pipelines I've had trouble getting my head around DSPy in...
#geospatial #gis #ai #prompt-engineering #generative-ai #llms #drew-breunig #overture #dspy […]
AGI is just around the corner!
I'm learning to use DSPy with GEPA (Genetic-Pareto) prompt optimization. In GEPA a larger "teacher" LLM adjusts the prompt for a smaller "student" LM to perform a specific task as well as possible. The teacher will try many different prompts and evaluate the […]
I had two choices: rewrite 20+ years of expertise @rubyonrails.org.web.brid.gy in Python, or bring the power of #DSPy to the Ruby community to write sophisticated AI Agents and Workflows.
I went for Ruby.
#rails #ruby #dspy
heyvicente.medium.com/stop-wrestli...
Context Engineering — A Comprehensive Hands-On Tutorial with DSPy Let's dissect the art and science of context engineering, one module at a time! The post Context Engineering — A Comprehens...
#Large #Language #Models #Context #Engineering #Deep […]
[Original post on towardsdatascience.com]
The angelic @collectiwise.bsky.social captured here at Mic rosoft's #LangChain event on Tuesday. JC is developing an extraordinary #AgenticAI enabled Data Warehousing system towardspeople.co.uk/agents-for-d...
#AgenticAI #DataWarehousing #Compliance #LangGraph #DSPy #GDPR #HIPAA #PCI #BigQuery #DBT
DSPy for Prompt Engineers: Build Your First Modular LLM Program (OpenAI & Llama) No More Prompt Tinkering: 3 Steps to a Self-Improving JSONL Q/A Agent with DSPy Part 1 – Hello DSPy: Building ...
#dspy #openai
Origin | Interest | Match
Let the Model Write the Prompt | Drew Breunig #dspy #promptengineering #llms #generativeai
Demo of using #LLM with #DSPy (love the programming vs prompt engineering for dev's) and #MCP, checking Jira duplications and even opening a Jira ticket. By Guy Dahan of NVIDIA at Geektime Code
Have you heard the news? #MLflow now supports tracking for DSPy optimization workflows—just like it does for #PyTorch training!
Keep reading to see what this means for your #LLM projects… 👇
#opensource #dspy #oss
Unlock the next level of #GenAI at #DataAISummit! 🚀
Catch Chen Qian’s lightning talk on how #MLflow + #DSPy can transform GenAI app dev with autologging, full observability, and end-to-end #MLOps.
🗓️ June 9-12
📍 San Francisco, CA
Register: databricks.com/dataaisummit
#opensource #oss
We showcased MLflow’s GenAI features (Prompt Registry, Tracing, Evaluate) and introduced #DSPy for optimizing #LLM prompts! 🤖
Bilibili’s engineers were excited about adopting MLflow + Databricks monitoring capabilities and were excited by the open source ecosystem we’ve built! 🌎🚀
#opensource #oss
📣 TODAY at 4PM PT - MLflow Community Meetup!
🔗 Register today 👉 lu.ma/mlflow423
Join the global MLflow community for two exciting tech deep dives:
🔹 MLflow + #DSPy Integration
🔹 Cleanlab + #MLflow
🎥 Streaming live on YouTube, LinkedIn, and X
💬 Live Q&A with the presenters
#opensource #oss
Whether you’re tuning a prompt or training a model, MLflow helps you understand what’s happening under the hood — so you can iterate faster and build better. ✅
MLflow documentation ➡️ mlflow.org/docs/latest/...
#mlflow #dspy #opensource #oss
MLflow now supports tracking for #DSPy (Community) optimization — just like it does for @pytorch.org training! 🙌
#MLflow is the first to bring full visibility into DSPy’s prompt optimization process. More observability, less guesswork.
Get started today! ➡️ medium.com/@AI-on-Datab...
#opensource
With MLflow 2.20, you can explore traces without ever leaving your notebook. 🌟
That means: No more tab switching. Just streamlined observability, right where you're working. ✅
Whether you're using LangChain, #DSPy, or other frameworks, MLflow Tracing works out of the box—no code changes required!
Join us for the next MLflow Community Meetup — Wednesday, April 23 at 4PM PT! 🗓️
🔹 Explore the new MLflow + #DSPy integration
🔹 Learn how Cleanlab adds trust to AI workflows with MLflow
💬 Live Q&A + demos
📺 Streamed on YouTube, LinkedIn, and X
👉 RSVP: lu.ma/mlflow423
#opensource #mlflow #oss
Finally getting a handle on #DSPy for simple use-cases! I've even built out a module or two.
Built this today to understand better how a few of the optimizers work under the hood:
github.com/BenMcH/DSPy-...
I continue to be impressed by how #DSPy so elegantly removes prompt engineering from my workflow and makes LLMs feel like a universal API.
Even better, the optimizers are built in TDD (really, metric driven development)
#ITByte: #DSPy is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs).
It unifies techniques for prompting and fine-tuning LMs — and approaches for reasoning, self-improvement, and augmentation with retrieval and tools.
knowledgezone.co.in/posts/Intro-...
Getting used to #SystemsThinking youtu.be/vRTcE19M-KE?... #PromptModel #Interoperability #SystemsDesign #DSPy
Generating a Glossary from a Jekyll Blog Using DSPy & Claude #dspy #pydantic #glossary #tutorial #llms
Read Drew’s glossary for definitions of AI terms and articles referencing them. And, use his code to make your own glossary. And, read his explanation of the technique to build other projects of your own work on your own words!
#WordsMatter #DSPy #Jekyll #LLM #ClaudeHaiku #AI #Python
Pipelines & Prompt Optimization with DSPy #llms #dspy #promptengineering
