DSPy Logo

DSPyWeekly

Your Weekly Dose Of All Things DSPy

Articles and Tutorials
Videos
Every Friday

You'll receive verification email in max 1 minute. Do check SPAM just in case. Unsubscribe anytime.

Subscribed by employees and students at

Apple
Microsoft
LinkedIn
Columbia University
JioStar
Freshworks
Netflix
Databricks
MIT

".@DSPyOSS is so good that i'm kind of sad how many hours i spent struggling without it last year"

Joshua Weaver
Joshua Weaver
Director @txoji Attorney with a background in tech and entrepreneurism.

"Both DSPy and (especially) GEPA are currently severely under hyped in the AI context engineering world."

tobi lutke
Tobi Lutke
CEO by day, Dad in evening, hacker at night.

"We've reached that stage where every single day of the week (and every weekend), there are *several* really cool @DSPyOSS research papers, open-source applications, production use cases, or deep-dive tutorials, etc."

Omar Khattab

DSPyWeekly Issue No #17

Published on January 09, 2026

📚 Articles

Moderating Discord with DSPy | Isaac Miller's Blog

"Discord Mod," Isaac B. Miller details his technical experiment to create a custom AI chatbot tailored specifically for his private Discord server. The project involved scraping and processing years of chat logs to build a dataset that captured the unique slang, inside jokes, and distinct communication styles of his friend group. Miller explains the workflow of cleaning this data and using it to fine-tune an OpenAI GPT-3 model, aiming to generate a bot that could seamlessly blend into the conversation.

Experiences from Building Enterprise Agents (with DSPy and GEPA) | Slavozard's blog

DSPy and GEPA provide a lot of room here to quickly iterate and get validation about what works and what does not. This enables me to iterate and refine my data, evals, and finally the architecture.

How DSPy Optimizes Prompts - Mindfire Technology

In this post, we’ll show you how DSPy can optimize prompts using MIPROv2. We’ll go from an instruction that gives poor results to one that gives consistently correct results — and we’ll show you exactly what changes along the way. You’ll see how the model’s instructions and examples evolve, and why this makes your LLM programs more reliable.

PAPER: ContextLeak: Auditing Leakage in Private In-Context Learning Methods

In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensitive information, reliable privacy-preserving mechanisms are essential to prevent unintended leakage through model outputs. Many privacy-preserving methods are proposed to protect the information leakage in the context, but there are less efforts on how to audit those methods. We introduce ContextLeak, the first framework to empirically measure the worst-case information leakage in ICL. Uses DSPy and GEPA.

LLM-Guided Evolutionary Kernel Optimization: From Research to Production KernelsYep!

A technical discussion of how large language models can speed up GPU kernel optimization, from research ideas to production kernels. DSPy used in knowledge pipeline and has a mention.

DSPy Haystack Integration Claude Code Skill - Optimize RAG

This skill bridges the gap between the Haystack orchestration framework and DSPy’s optimization engine, allowing developers to automatically tune prompts for RAG pipelines instead of relying on manual trial and error. It provides a structured workflow to wrap Haystack retrievers in DSPy modules, define custom metrics for evaluation, and extract optimized few-shot examples to re-integrate into production Haystack pipelines.

🎥 Video

DSPy Interview Series: DSPy, BAML and Benchmarks: DSPy Interview Series with Prashanth Rao

In this video Prashanth Rao talks about his contribution to DSPy codebase and in the course of doing so gives us a walkthrough of BAML, it's toolchain, playground and how it works end to end. He also gives a quick peek into his benchmark numbers on structured outputs in different formats.

Conversation with Mike - Author, Marketer and Engineer ( DSPy Interview Series )

Mike is a "multi-hyphenate" tech entrepreneur who bridges the gap between marketing and AI engineering. Former founder of ... | Channel: Information Shelf

DSPy: The End of Prompt Engineering - Kevin Madura, AlixPartners

Applications developed for the enterprise need to be rigorous, testable, and robust. The same is true for applications that use AI, ... | Channel: AI Engineer

Omar Khattab on the State of DSPy

Omar Khattab explains the philosophy driving DSPy. It's not just for prompt optimization; it's about turning AI software into an ... | Channel: cmpnd

🚀 Projects

vicentereig/a2ui-rails

A2UI for Rails - LLM-driven UI generation with DSPy.rb and Turbo Streams | Language: Ruby

ManhLQ/sentiment-detection

A simple sentiment detection with DSPy | Language: Python

jmanhype/rec-praxis-rlm

Procedural memory + REPL context for DSPy 3.0 autonomous agents | Language: Python | License: MIT License

AK0126/HINTy

Math hint generation with DSPy | Language: Jupyter Notebook

ZIsekenegbe/DSPython

Collection of projects from my intro to python for data science course

jatinshah/sec-filings-api

Structured access to SEC EDGAR data with intelligent parsing using DSPy for enhanced data extraction | Language: Python | License: Other