Notes from the team
BAML thoughts.
Insights, tutorials, and updates from the BAML team. Stay ahead with the latest in AI development.
Get the latest posts delivered to your inbox.
Browse by category
All posts
47 articles
How 6 engineers built 6 BAML SDKs for 6 programming languages in 1 week
Sam LijinHow we navigated 12 pivots without hating each other
Vaibhav GuptaConstrained decoding seems like the greatest thing since sliced bread, but it often forces models to prioritize output conformance over output quality.
Sam LijinDon't ask it to add a confidence score. Don't add it to sum up items on a receipt. Don't ask it to confirm how many rows there are in a PDF.
Sam LijinTOON is a new serialization format, but has many pitfalls.
Sam LijinPost-mortem of the 0.212.0 timeouts incident
Greg HaleHow BAML makes tools calls easy to integrate into apps
Greg HaleGuidance on dealing with entity IDs in LLM functions
Greg HaleNotes from our 2024 Prompting Workshop
Vaibhav GuptaExploring the fascinating world of Wasm, Zed extensions and LSP
Egor LukiyanovEnvironment variables in BAML are not as simple as they seem. It's tricky to pass and read them from the generated languages runtime. This post talks about how we solved this problem by lazily loading them!
Rahul TiwariSpecify complex workflows directly in BAML
Greg HaleA new take on Agentic frameworks
Greg HaleAn end-to-end agentic chatbot tutorial for React devs
Greg HaleHow to do tool-calling or function-calling with Llama API (with reasoning)
Vaibhav GuptaHow to do tool-calling or function-calling with Llama 4
Vaibhav GuptaHow to use QwQ 32B to do function calling or tool calls
Aaron VillalpandoAuto generated React hooks for your BAML functions
Chris WattsHow to do tool-calling or function-calling with Gemini 2.0
Aaron VillalpandoHow to do tool-calling or function-calling with o3-mini
Vaibhav GuptaRoadmap to BAML 1.0
Vaibhav GuptaSemantic Streaming
Greg HaleType System
Antonio SarosiBAML Chat
Sam LijinVS Code LLM Playground 2.0
Aaron VillalpandoA proposal for a new way to build AI applications and agents
Vaibhav GuptaJoin us on January 27-31
Vaibhav GuptaHow to do tool-calling or function-calling with Deepseek R1
Vaibhav GuptaBAML is now supported in Cursor
Sam LijinHow to use Open AI O1 to do function calling or tool calls
Vaibhav GuptaBAML now supports parsing triple-backtick code blocks in LLM outputs
Sam LijinUse BAML to evaluate your LLM applications regardless of the language you use to call them
Greg HaleModify LLM response models at runtime.
Aaron VillalpandoA survey of every framework for extracting structured output from LLMs, and how they compare.
Sam LijinA new technique for streaming structured output from LLMs
Aaron VillalpandoBAML now integrates with OpenAPI, allowing you to call BAML functions from any language.
Sam LijinGetting structured output out of Ollama, using novel parsing techniques.
Sam LijinWe leveraged a novel technique, schema-aligned parsing, to achieve SOTA on BFCL with every LLM.
Vaibhav GuptaA technical explanation of every way to extract structed data from an LLM
Vaibhav GuptaExposing the inner workings of BAML
Anish PalakurthiAn overview of the work that goes into building a new programming language.
Sam LijinCapturing Non-Text Information and Richer Context with LLMs
Anish PalakurthiApplying structure to Gemini output with BAML
Anish PalakurthiHow to do RAG with Ruby streaming AI APIs
Sam LijinHow to do RAG with NextJS streaming AI APIs
Aaron VillalpandoA deep-dive into how to use type-definitions instead of json schemas in prompt engineering to improve accuracy and reduce costs
Aaron VillalpandoBAML is a lightweight programming language to help perform structured prompting in a typesafe way.
Vaibhav Gupta