Baml: The Programming Language for Agents

This isn't needed at all. If "AI" is half as good as we're reliably inform it is, "AI" can write anything you want in any language or combination of languages you want. It's got near infinite short term memory, no 5+-2 working memory limit, no cognitive biases, and it's the worst it's ever going to be.

Straight up imperative language programming would work. No need for crutches like object orientation, structured programming etc etc. Probably no need for any methodology. LLMs can't stand up, as it were, so agile isn't helpful.

didn't expect someone to post us here yet, we're still working on our launch!

We have been building BAML for around 3 years -- originally it was a DSL for getting structured outputs from llms using what we call 'llm functions'

Our users told us they wanted to do more, so we made it an actual turing-complete language, still with a focus on people building AI workflows and calling nondeterministic models. This is why we added very flexible testing capabilities into BAML itself for test parameterization, dynamic tests, etc.

As we were building it, we realized humans weren't going to be the ones writing the code, so we started researching what we could do on this front. This led us to design BAML to use all fully-qualified-names for everything (classes, enums,functions etc) to name one example. We found in some cases AI agents saved 30% tokens navigating baml codebases vs TypeScript ones. There's no imports to track down, etc.

We do aim to keep humans in the loop, and we'll do some more deep dives that tackle each feature.

Indeed! Why not? The reason why humans need variables, functions, types, etc are all cognitive limitations of the human brain. "AI" should not be helped by those constraints.

Less ironically, because LLMs need the patterns of human cognition embodied in source. There's just not enough well commented assembly to train LLMs to imitate.