DsPy the Declarative Programming making prompts go brrrrrrr : Jayita Bhattacharyya
abstract:
DSPy is a declarative framework for building modular AI software. Allows you to iterate fast on structured code, rather than brittle strings, and offers algorithms that compile AI programs into effective prompts and weights for your language models. Whether you're building simple classifiers, sophisticated RAG pipelines, or Agent loops. This makes AI software more reliable, maintainable, and portable across models and strategies. Instead of wrangling prompts or training jobs, DSPy enables you to build AI software from natural-language modules and to generically compose them with different models, inference strategies, or learning algorithms.
speaker bio:
Jayita Bhattacharyya, a Generative AI Engineer, international conference speaker, and Co-Organizer of the Bangalore Python User Group, one of India's largest Python communities under the Python Software Foundation ecosystem. Jayita specializes in Agentic AI, RAG systems, Knowledge Graphs, and production AI engineering, and has spoken at global conferences including PyData Global, PyCon Finland, Open Source India, NVIDIA AI Inference Day, and Open Source Summit AI_dev Europe. Known for combining deep technical expertise with practical industry insights, she is passionate about helping organizations and developers build reliable, scalable, and impactful AI systems.