The Boundary Blog
Learn about the latest updates to Boundary's toolkit
Transparency as a Tenet
Exposing the inner workings of BAML
![](/profile-anish.png)
Anish Palakurthi
Building a New Programming Language in 2024, pt. 1
An overview of the work that goes into building a new programming language.
![](/profile-sam.png)
Sam Lijin
Use Audio with your LLMs!
Capturing Non-Text Information and Richer Context with LLMs
![](/profile-anish.png)
Anish Palakurthi
Announcing Gemini Support!
Applying structure to Gemini output with BAML
![](/profile-anish.png)
Anish Palakurthi
Building RAG in Ruby, using BAML, with streaming!
How to do RAG with Ruby streaming AI APIs
![](/profile-sam.png)
Sam Lijin
Build RAG with citations in NextJS (with streaming!)
How to do RAG with NextJS streaming AI APIs
![](/aaronv.jpg)
Aaron Villalpando
Every Way To Get Structured Output From LLMs
A survey of every framework for extracting structured output from LLMs, and how they compare.
![](/profile-sam.png)
Sam Lijin
Your prompts are using 4x more tokens than you need
A deep-dive into how to use type-definitions instead of json schemas in prompt engineering to improve accuracy and reduce costs
![](/aaronv.jpg)
Aaron Villalpando
Announcing BAML - The typesafe interface to LLMs, with built-in testing, guardrails and observability
BAML is a lightweight programming language to help perform structured prompting in a typesafe way.