platoseedplatoseed
The programming language for AI
Boundary is building BAML -- a programming language to build AI agents. We used to code in assembly, and moved on to C. From C, we moved on to higher level languages like Python. Now we are going from Python to natural language. What does the code look like when 50% of the business decisions is decided by an AI agent / prompts? How do you test these AI components? We made BAML to address these problems. BAML helps has built-in tools to test, observe, and work with structured LLM outputs / tool calling natively in the language 10x faster. With BAML you can also instantly parallelize LLM Calls, or react to certain events or changes in your pipelines, without having to write any boilerplate. It's like using 'React' for AI. BAML code can used from any other language -- providing a standardized way to organize and declare any LLM or AI code.
BAML Boundary provides a programming language and tooling for building AI applications with type safety and reliability. It generates native code in the user’s language of choice and integrates with multiple LLM providers and runtimes to improve AI pipeline reliability.
BAML is a language and toolchain that lets developers define AI interfaces and prompts with type-safe schemas, generating TypeScript types and native code in languages like Python, TypeScript, Ruby, and Go. It supports structured outputs (JSON, XML, YAML), automatic retry and fallback, testing in CI/CD, and a VSCode extension. Users can define prompts as schemas, generate native functions, test them in a playground, and deploy agents across multi-cloud environments by generating code that can run in the developer’s language of choice without special deployment steps.
Who it’s for: Developers building AI applications who require type safety, structured outputs, and reliable AI pipelines across multiple languages and LLM providers.
Hiring/traction mentions on site (references to tests, playground, CI/CD testing, VSCode extension) and large-scale adoption testimonials
Vaibhav is a software engineer with over 7 years of experience building innovative products. At Microsoft, he worked on realtime 3D reconstruction for HoloLens, gaining expertise in computer vision and 3D graphics. At Google, he led performance optimization on ARCore and Face ID, significantly improving latency and quality. Now he's bringing that same experience to help bring better quality and speed to Generative AI technology. For talking anything Computer Vision/AI/Performance, reach out!
AmazonAaron has worked for the better part of a decade scaling out distributed systems at AWS and launching full-stack consumer facing products at Prime Video. He is now passionate about building scalable ML infrastructure and the best developer experience at Gloo.
We help LLMs like ChatGPT connect to knowledgebases and add mechanisms to stop them from hallucinating..
Gloo offers a managed solution to build a knowledge graph for LLMs, providing a searchable API (keyword and semantic search) and an API (Check-GPT) to validate LLM answers against a private knowledgebase. The product targets developers needing data security and reduced hallucinations, with a dashboard to manage embeddings, search parameters, and analytics.
From the original launch (Mar 2023) — may be outdated.
Formerly “Gloo”, “Gloo Chat” · why startups rename →
The improvement engine for AI agents
Use AI tools without fear of data leakage
