Boundary ML
@boundaryML
Followers
763
Following
38
Media
3
Statuses
80
Developing BAML, the AI framework that puts the engineering back into prompt engineering.
Joined January 2023
We decided to make our function-calling benchmark results fully public and interactive!.
Our interactive function-calling benchmark results are live! .
1
2
9
Keep the BAML projects coming.
When I worked at @TetraScience I learned how to use @elastic. Something I found a bit strange, however, is just how poorly documented regular human queries were paired to ElasticSearch (EQL) language queries. I decided to do something about this.
0
0
3
RT @andrew_d_d: Home automation is a >$100B industry. With open source LLMs on @CerebrasSystems, anyone can run blazingly fast inference ba….
0
1
0
RT @doesdatmaksense: was living under the rock to have never heard about BAML. thanks to @tech_optimist for introducing me to BAML, have be….
0
2
0
RT @0xblacklight: I built an open-source deep research agent with Gemini, @ExaAILabs and @boundaryML's BAML + a terminal UI. (also has a s….
0
7
0
RT @kuzudb: This post shows the beginnings of an agentic Graph RAG workflow that's more robust to a broader range of user questions. No age….
0
2
0
RT @udbhhav: Its crazy how easy @boundaryML has made making AI agents. After trying Agno, langchain etc I am convinced BAML is the best w….
0
2
0
RT @aaron__vi: What if you did all LLM evals on a spreadsheet? . Made with BAML by AndrewD on our discord
0
1
0
Read how we are changing the game in LLM Observability.
If an API failed 5% of the time, engineers would fix it immediately. So why do we accept that from LLMs? @boundaryML is changing that with BAML, a typed programming language for LLM workflows—and @ClickHouseDB as the observability layer behind it all.
0
0
2
RT @smkalami: 👩💻 Still writing LLM prompts with f-strings?. That might’ve worked early on — but today’s AI apps demand structure, speed &….
0
2
0
RT @hellovai: over 300 ai engineers came to our 3 hour workshops. They asked for another one. next 4 weeks, 1 hour every tuesday:🦄 ai tha….
0
4
0
Gemma models are crushing it. Read more on how BAML was used to compare Gemma with OpenAI at classification tasks.
In this post, I wrote about a case study I did using #BAML (by @boundaryML) that compares the performance of LLMs like Gemma-3 and gpt-4o-mini, to enrich a dataset via a gender classification task. Can LLMs do better than a classical ML-based gender API?.
0
2
7
RT @hypermodeinc: Seattle AI Hack Night Recap, feat. demos by @boundaryML + @flyteorg @union_ai + @neo4j + @lyonwj. Read / watch here: htt….
0
1
0
RT @tech_optimist: @boundaryML somehow managed to do both at the same time AND keep DevEx at the forefront 💪🏽.#BAML.
0
1
0
March 25th - SF. 5 YC founders from companies like @deel, @ProductHunt, and @mintlify along with our founder @hellovai will be sharing everything about the what being a founder is like.
YC event March 25! . Yesterday, I talked to a W25 founder who hadn't talked with anyone whose startup failed(!). Most YC startups fail, but we often don't talk about that part of the founding journey. I'm really glad @deel and @brexHQ are teaming up to do an event on the
0
1
3
New RAG Example in our docs!.
just submitted a PR to the #BAML repo for a minimal RAG example, and it's been published on the @boundaryML docs page - give it a look and try it out!.1/5 🧵👇🏽.
0
0
5
RT @tech_optimist: Here's an example of why #BAML by @boundaryML is an amazing alternative to prompting via Python libraries. This example….
0
2
0
RT @ChiefScientist: Join @neo4j and @boundaryML to learn about BAML -- and generate graph data with it!.
0
3
0
More than 15 AI companies from YC F24 batch are using BAML. If you're in W25, we'd be happy to demo and help with your prompts!.
if you're not using BAML, you're doing it wrong. @boundaryML.
0
3
14
RT @aaron__vi: Final day of Launch Week, and we just crossed 2000 ⭐️ on Github 🚀. Today, we’re more than excited to unveil our vision and w….
0
7
0
Day 4 required some tough engineering, but we made it happen.
Launch week: Day 4. Introducing 💫Semantic Streaming of LLM outputs. No more token-based streaming!. BAML now lets you stream JSON properties with precise control—stream objects only when complete, choose atomic or partial updates, and avoid nulls. Demo below 👇
0
1
4