We decided to make our function-calling benchmark results fully public and interactive!

lets go!!

The Seattle Rust User Group meetup is on Thursday, June 18 at 6pm PT, hosted by @boundaryML. @conradirwin from Zed is giving a talk on CRDTs, alongside talks from @boundaryML and the Seattle Rust community. RSVP: meetup.com/seattle-rust-user…

At @boundaryML We're building building a full compiler, VM and async runtime. Kinda like TypeScript V8 Node.

marginally manageable is the highest form of flattery

We are launching a programming language built for agents soon called BAML that has been in the making for 1 years. You can follow @boundaryML We are a small team of 6 developing it with care, gathering feedback from humans and agents. Fully Open Source. If you are interested DM me for early alpha access.

I benchmarked a new extraction harness on a private eval dataset for lerim-cli (new version is out now - v0.1.83) and the main lesson was very clear: if you want smaller models to work well, you should stop asking the model to do everything and start doing more engineering work. Before, the agent was closer to a single-pass PydanticAI setup: read a large trace, understand what matters, decide what is durable memory, call tools correctly, stay inside the context window, and output clean structured records. That puts too much burden on the model, especially when you want to use smaller or cheaper models. The new harness is BAML (@boundaryML) LangGraph (@LangChain). The graph now does more of the deterministic work: - read the trace in windows - ask the model to scan one window at a time - keep compact findings instead of the whole trace - synthesize memory records only at the end - validate/retry typed BAML outputs - persist with normal code, not model improvisation So the model is not the whole agent anymore -> It is one reasoning component inside a more engineered system. On the private benchmark, using the same MiniMax M2.7 model, the new harness completed all cases while the old harness had multiple failures from tool retries and context window issues. - Task completion: BAML LangGraph completed 100.0% vs PydanticAI at 72.73%, a 27.27 point lead. - Case failures: BAML LangGraph had 0 failures vs PydanticAI with 6, meaning 6 fewer failures. - Episode count rate: BAML LangGraph reached 100.0% vs PydanticAI at 81.25%, a 18.75 point lead. - Record budget rate: BAML LangGraph reached 46.88% vs PydanticAI at 28.12%, a 18.76 point lead. - Concept recall average: BAML LangGraph scored 0.428 vs PydanticAI at 0.2598, a 0.1682 improvement. - Quality average: BAML LangGraph scored 0.3352 vs PydanticAI at 0.318, a 0.0172 improvement. - Tool call errors average: BAML LangGraph had 0.0625 vs PydanticAI at 1.9688, much better. Quality is not solved yet. It is only slightly better overall and still needs better pruning before persistence. But robustness improved a lot. This is the direction I think specialized agents should go: smaller models, more deterministic scaffolding, less magical thinking about one giant prompt doing the whole job. Next step is to make this work well with models people can run locally. A new version of Lerim-cli is now released with the extract agent refactored to use Langgraph BAML. Next agents will be refactored as well soon in the next releases. github.com/lerim-dev/lerim-c…

Refactoring is definitely much easier now. Here's how i used agents to refactor our entire compiler ( 65k, -117k, 74 commits). 1. Forked parallel crates (foo --> foo2) 2. Strict dependency firewall (enforced via precommit) 3. Audited core data structures first <-- took time

Announcing the BAML Bounty... For all power-users of BAML, we're giving away free BAML merch! (t-shirts, stickers, hoodies 🔥🧯). Share what you built with BAML with #baml → Fill out tally.so/r/PdErze → Free merch! Hurry! Supplies are limited to the first 50 posts.

Looking for designers who have Blender experience! Will pay ~$500 for a single asset

RT @anishpalakurT: Hiring an absolutely cracked video editor for something big @boundaryML... DM me and follow so I see it! 👇

If you read papers like this for fun you'll fit right in @boundaryML Join us, we're growing

Whats your favorite language feature and why is it match?

syntax makes a huge difference to how good coding agents are, and languages should be rethought. some great learnings from rust and go! great post by @aaronvi

Hot take: building agents without BAML in 2026 is like training models without Jupyter notebooks in 2020. Technically possible? Sure. But why would you torture yourself? Type-safe prompts. Instant playground testing. Multi-language support. promptfiddle.com

This is what we're building. BAML — the first language designed for AI-native software. promptfiddle.com

🤝@zeddotdev

How to bundle BAML by @boundaryML Nitro for @vercel deployment

In the next version of BAML (0.215.0), you will be able to optimize your prompts using GEPA `uv run baml optimize`. Thanks to @imalsogreg

Cool tutorial with end-to-end structured extraction for Patient intake forms using #BAML @boundaryML @cocoindex_io. Production-grade, Fully #OpenSource. get started: 🔗 cocoindex.io/blogs/extractio… repo: 🌟 github.com/cocoindex-io/coco… > BAML defines a typed Patient schema role-correct PDF prompt (critical for OpenAI providers). > CocoIndex orchestrates file input, transformation, and incremental indexing. 📄 What the tutorial covers •  Defining a FHIR-inspired patient schema in BAML •  Configuring Gemini 2.5 Flash for structured extraction •  Generating the Python client with baml-cli •  Writing a CocoIndex flow that ingests PDFs, calls the BAML function, and exports to Postgres •  Leveraging incremental processing caching for real-world scale •  Debugging lineage using the CocoInsight UI (now in free beta) #LLM #KnowledgeGraph #RAG #GraphDatabase #GraphAI #OpenAI #AIInfra #DevTools #DataPipelines #RealtimeAI #VectorDB #LLMApplications #GenerativeAI #AIEngineering #Python #AI4Docs #SemanticSearch #Rust #cplusplus