dotAI 2025
who it's for
ML engineers, ML platform engineers, MLOps engineers, data engineers, AI researchers, engineering managers
topics
typed model programming APIs; multi-agent stack deployments; retrieval-augmented generation pipelines; model quantization and compilation; inference caching strategies; production benchmarking with MLflow; vector index integrations; computational graph DataOps; experiment tracking and scoring; incident-triage and repair agents
| title | author | length |
|---|---|---|
| BAML: a new programming language for AI | Vaibhav Gupta | 19m |
A new language claims to turn LLM calls into typed functions so models behave like normal code with BAML files, test cases, a run button and flexible parsing… | ||
| Databricks | Viktoria Semaan | 19m |
Databricks unveils agent bricks, a packaged multi‑agent stack that builds RAG pipelines, converts text to SQL, and auto‑benchmarks with MLflow 3. Demo shows a… | ||
| Pruna AI | Bertrand Charpentier | 10m |
Pruna AI applies the open source pruna tooling to compress models by combining quantization, caching, compilation and factorization, turning a Flux Context… | ||
| Anthropic | Alex Palcuie | 23m |
Claims production agents can triage incidents, fix code, and deploy exist but are partial: Claude Code and Claude agent SDK already generate and patch Python… | ||
| Skrub DataOps, Probabl | Gael Varoquaux | 20m |
Claims that messy data science code yields 88% of projects failing to reach production and that the fix is better primitives, not new models. Demonstrates… | ||
| nothing matches | ||