DSPy in Production¶
DSPy is in production at Shopify, Databricks, Dropbox, JetBlue, Moody's, AWS, Sephora, VMware, and dozens more.
This list represents companies that have publicly shared their use cases or have provided permission to be included. It reflects a selection of the many industry applications of DSPy currently in production. To add yours, please open a PR.
Featured case studies¶
~550× cost reduction
Scaled DSPy + GEPA for structured metadata extraction across all Shopify shops.
Relevance judge, automated
Optimized Dash's relevance judge with DSPy for retrieval ranking and offline evaluation.
All companies¶
| Company | Use case |
|---|---|
| Shopify | Structured metadata extraction across all Shopify shops with DSPy + GEPA; reduced yearly costs ~550×. Talk |
| Dropbox | Optimized Dash's relevance judge using DSPy across ranking, training data generation, and offline evaluation. Engineering blog, Talk |
| AWS | Migrates prompts from larger to smaller models on Amazon Nova while maintaining performance. Blog |
| JetBlue | Multiple chatbot use cases. Blog |
| Replit | Synthesize diffs using code LLMs using a DSPy pipeline. Blog |
| Databricks | Research, products, and customer solutions around LM judges, RAG, classification, and other applications. Blog |
| DDI | Leadership coaching agents built on Databricks with DSPy. Customer Story |
| Sephora | Undisclosed agent usecases; perspectives shared in DAIS Session. |
| Zoro UK | E-commerce applications around structured shopping. Portkey Session |
| VMware | RAG and other prompt optimization applications. Interview in The Register. Business Insider. |
| Nous Research | Evolutionary self-improvement for the Hermes agent: optimizes skills, prompts, and code using DSPy + GEPA. GitHub |
| Haize Labs | Automated red-teaming for LLMs. Blog |
| Plastic Labs | R&D pipelines for Honcho. Blog |
| PingCAP | Building a knowledge graph. Article |
| Salomatic | Enriching medical reports using DSPy. Blog |
| Truelaw | How Truelaw builds bespoke LLM pipelines for law firms using DSPy. Podcast |
| STChealth | Using DSPy for entity resolution including human-readable rationale for decisions. |
| Moody's | Leveraging DSPy to optimize RAG systems, LLM-as-a-Judge, and agentic systems for financial workflows. |
| Normal Computing | Translate specs from chip companies from English to intermediate formal languages |
| Procure.FYI | Process messy, publicly available technology spending and pricing data via DSPy. |
| RadiantLogic | AI Data Assistant. DSPy is used for the agent that routes the query, the context extraction module, the text-to-sql conversion engine, and the table summarization module. |
| Raia | Using DSPy for AI-powered Personal Healthcare Agents. |
| Hyperlint | Uses DSPy to generate technical documentation. DSPy helps to fetch relevant information and synthesize that into tutorials. |
| Starops & Saya | Building research documents given a user's corpus. Generate prompts to create more articles from example articles. |
| Tessel AI | Enhancing human-machine interaction with data use cases. |
| Dicer.ai | Uses DSPy for marketing AI to get the most from their paid ads. |
| Howie | Using DSPy to automate meeting scheduling through email. |
| Isoform.ai | Building custom integrations using DSPy. |
| Trampoline AI | Uses DSPy to power their data-augmentation and LM pipelines. |
| Pretrain | Uses DSPy to automatically optimize AI performance towards user-defined tasks based on uploaded examples. |
| Spindle AI | Turns natural-language constrained optimization problems into solvable mathematical programs whose candidate solutions are scenarios. |
| Infinitus | Leverages DSPy to build and optimize healthcare AI agents |