Declarative LLM Engineering with DSPy and Dagster

Description

Data Engineering Theatre Thursday, 25th Sep 12:00 - 12:30 Data teams know the pain of moving from proof-of-concepts to production. We’ve all seen brittle scripts, one-off notebooks, and manual fixes turn into hidden risks. With large language models, the same story is playing out, unless we borrow the lessons of modern data engineering. This talk introduces a declarative approach to LLM engineering using DSPy and Dagster. DSPy treats prompts, retrieval strategies, and evaluation metrics as first-class, composable building blocks. Instead of tweaking text by hand, you declare the behavior you want, and DSPy optimizes and tunes the pipeline for you. Dagster is built on a similar premise; with Dagster Components, you can build modular and declarative pipelines. This approach means: - Trust & auditability: Every LLM output can be traced back through a reproducible graph. - Safety in production: Automated evaluation loops catch drift and regressions before they matter. - Scalable experimentation: The same declarative spec can power quick tests or robust, HIPAA/GxP-grade pipelines. By treating LLM workflows like data pipelines: declarative, observable, and orchestrate, we can avoid the prompt spaghetti trap and build AI systems that meet the same reliability bar as the rest of the stack. Pedram Navid Head of Marketing and DevRel, Dagster Labs Pedram Navid is the Head of Marketing and Developer Relations at Dagster Labs, where he bridges the gap between data engineering practices and developer communities. Before joining Dagster Labs, Pedram built a career as a data engineer and open-source advocate, with hands-on experience deploying data platforms at scale in high-growth environments. His passion lies in empowering data practitioners with the tools and insights they need to build resilient, scalable systems.