# BAML Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/baml
> Markdown URL: https://aitinkerers.org/technologies/baml.md
> Technology record last updated: 2026-09-18T15:13:40Z
> Generated: 2026-09-21T17:46:19Z

BAML (Basically a Made-up Language) is the domain-specific language (DSL) that transforms LLM prompts into type-safe, polyglot functions for reliable, structured output generation.

BAML is the open-source DSL developed by Boundary to bring engineering rigor to AI workflows. It converts raw prompts into first-class, type-safe functions, eliminating the complex parsing boilerplate and ensuring reliable structured data extraction from any LLM (including OpenAI, Anthropic, and local models). Built on Rust, BAML provides a unified, high-speed development experience with native tooling, such as the VSCode Playground, which allows developers to test and iterate on prompts up to 10x faster. The resulting code is polyglot, generating clients for Python, TypeScript, Ruby, and Go, allowing teams to deploy robust, deterministic AI agents across diverse tech stacks.

- Official technology site: https://boundaryml.com/
- Public AI Tinkerers demos and talks: 12
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Putting a leash on LLM's with BAML](https://atlanta.aitinkerers.org/talks/rsvp_h6YMTIcqU7Q)

VibeKeys is a piano learning app designed to test the boundaries of interactive AI education capabilities. I am also testing the boundaries of building with AI in coding the app, which is 100% coded by AI, yet meticulously reviewed by a human. I’ll show an app demo where the student plays a section incorrectly, and how the voice AI agent is engaged to provide insight to the student through its multi-level agent orchestration and context engineering system. The app has an interactive context layer that allows low-latency responses for simple tool calling combined with more escalated handoff to a deep-reasoning “Music Education” agent. We will then walk through key code sections of the AI orchestration layer to see how easy BAML makes it to implement multi-agent LLM's with in-app tool-calling capabilities. Optional: A brief discussion of an AI skill I developed to curate project-specific principles that reflect the unique taste of your project and help the AI follow those principles across business, product, and technical domains.

- Event context: AI Tinkerers Atlanta x AI Collective: Community Demos at ATL Tech Week — 2026-08-13 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_h6YMTIcqU7Q

### [A context-aware interactive Piano tutor](https://atlanta.aitinkerers.org/talks/rsvp_Rf2oBe4bzK8)

VibeKeys is a piano learning app designed to test the boundaries of interactive AI education capabilities. I'l show an app demo where the student plays a section incorrectly, and how the voice AI agent is engaged to provide insight to the student through its multi-level agent orchestration and context engineering system. The app has an interactive context layer that allows low-latency responses for simple tool calling combined with more escalated handoff to a deep-reasoning "Music Education" agent. I could also show some of the cool AI tools and skills I use to build this project: - Project-Specific "Pattern Languages" (Christopher Alexander) to help guide decision-making - BAML (open-source AI wrapper infrastructure that turns all LLM calls into statically typed function calls). - My code review process which uses Reviewable.io to host the diffs and interactively communicate with the AI agent to address review issues.

- Event context: AI Tinkerers Atlanta: 2-Year Anniversary & Best Demos of the Year — 2026-07-30 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_Rf2oBe4bzK8

### [Automating Community Operations](https://seattle.aitinkerers.org/talks/rsvp_ibjALFX6YKw)

Foundations runs on a custom-built internal platform designed to automate the work typically handled by operations staff or project managers. At the center is an integrated agent that interacts directly with members through Slack and email—sending weekly updates, coordinating mentor sessions, answering questions, and managing access to tools and resources. Behind the scenes, the platform tracks member activity, manages billing, runs the application process, and structures the community’s collective knowledge. This presentation explores how automation and agent-driven workflows can operate a complex community with minimal manual coordination.

- Event context: AI Tinkerers Seattle: GTM Track — March — 2026-03-26 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_ibjALFX6YKw

### [Extracting RFC 5545 RRULE Compliant Schedule Data in valid JSON with only 0.6B Parameters](https://seattle.aitinkerers.org/talks/rsvp_DaYlLeV25ZU)

We have a vast amount of unstructured schedule data on community services available to communities across 20 states. It is easier for data managers and community members to write brief notes, though service delivery schedules can be quite complex when translated to data that is interoperable with the iCal standard. This makes it a great task for LLMs... but VRAM/RAM and compute is expensive, you know? I plan to probably show what a row of our data looks like, a community service offered for those in need and its unstructured schedule data. Then, I will take that unstructured data, prompt the model with it, and we can all see if it generated something useful. It will probably all be CLI but I will zoom in my screen ʕ•ᴥ•ʔ

- Event context: AI Tinkerers Seattle: January Meetup — 2026-01-31 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_DaYlLeV25ZU

### [AI Content Pipeline](https://sf.aitinkerers.org/talks/rsvp_1fasc8u4gw4)

we built something kinda cool and only gemini made it possible :)

- Event context: Mastering the Google AI Stack — 2025-08-15 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_1fasc8u4gw4

### [60min+ video -> automated mutli-channel content](https://seattle.aitinkerers.org/talks/rsvp_sJanirIc0ew)

We do 60-90 minute workshops on various AI techniques every friday and it takes ~5-8 hours afterwards to take all the content and prep a github readme, blogpost, readme, email, x posts, linkedin. So we thought, why not automate it. And now we do!

- Event context: AI Tinkerers Seattle – June Meetup — 2025-06-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_sJanirIc0ew

### [11.ai all the things](https://sf.aitinkerers.org/talks/rsvp_ysgcFSG-7K8)

The introduction of voice assistants and voice agents with MCP unlocks a whole new domain of product possibility. Paired with a user's context and their chat history, agents can integrate more seamlessly into out daily lives. This will be a demonstration of voice MCP for an AI home assistant. With only your voice, it can: - Turn on/off the lights - change the temperature of a thermostat, - provide information about various home-appliances and timers. Anything that can fit in an MCP

- Event context: AI Tinkerers - Voice Agents Science Fair — 2025-06-26 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_ysgcFSG-7K8

### [SPEAKER: Dexter Horthy, CEO of HumanLayer](https://nyc.aitinkerers.org/talks/rsvp_p-IjuRDwghQ)

Dexter, CEO of HumanLayer spoke at the AI Camp event.

- Event context: Advanced AI Engineering Camp with 🦄 ai that works — 2025-05-10 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_p-IjuRDwghQ

### [Tactician: Detailed, specific workplace advice for confusing or political situations](https://seattle.aitinkerers.org/talks/rsvp_gumR4iFgXLM)

I'm baking everything I learned through my PhD in Organizational Behavior and my years as a professor in the field, combined with my lifelong interest in organizational effectiveness, into Tactician. Tactician isn't a single advice-bot. It's a system that combines distinctly different perspectives, careful questioning and hypothesis-testing, and freeform chat to get you evidence-based, actionable advice. In the live demo I'll walk through a real workpalce scenario (people come to me for advice with these all the time). We'll chat with the advisor personas first. Then we'll give some further tailored details, based on an intake survey that's dynamically generated based on the chat. We'll see the combination of these piped back to the advisors, who will suggest little hypothesis tests in the real world so you can figure out what is actually going on. We'll simulate this in the demo. Once we're sure of the facts, the advisors present courses of action that seem likely to lead to a integrated good outcome: something that will be beneficial both for you and the organization. It's a system based on careful data selection, an agentic workflow (BAML, pydantic), RAG from a vector db with only the choicest organizational texts in it, and (eventually) fully local and private models to offer a complete tailored advice system. Starting by hooking it up to Claude 3.7 sonnet with some prompt engineering for multiple advice personas. Use-case spiel: Maybe you interacted with a boss or client recently who said something confusing but important. Maybe you're in a situation where people expect you to have a lot of people skills and you feel overwhelmed. Use Tactician to figure out a) what's going on, b) what your options are to get to a good outcome.

- Event context: AI Tinkerers Seattle - April Meetup — 2025-04-25 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_gumR4iFgXLM

### [Sales Intelligence Assistant](https://seattle.aitinkerers.org/talks/rsvp_w36HDtNPrT8)

This is a workflow I crafted to help me build a repository of knowledge based on the research I was conducting for validating BearHug’s market opportunities. Because BearHug is operating at the intersection of government and healthcare, it can get pretty complex and confusing to keep my facts and figures straight. I have used Perplexity to help me conduct research, but I don’t want the best knowledge to be lost to the void. So I developed a small script and workflow that allows me to use Perplexity to research a topic, identifying some of my favorite sources that it pulled from, then using Jina Reader I extract a TXT file of the wisdom contained within the webpage. If the content is a PDF, I download it and use Llama Parse to get good markdown out of it. Markdown is best for document retrieval, because it makes it very easy to decide where to chunk the documents, so I am planning to use some BAML to get structured markdown out of the TXT files I get from Jina. Then with all the markdown, I have had a good experience with Pinecone Assistants to help me process, chunk, and read the data from a vector store, making sure that I always have the best wisdom at my fingertips for this complex industry.

- Event context: AI Tinkerers Seattle - March Meetup — 2025-03-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_w36HDtNPrT8

### [Extract anything - from any model](https://seattle.aitinkerers.org/talks/rsvp_7iT1m_WKor4)

I'd like to share a demo showing off how we can take any document (PDF, Image, Text, audio, Video), and pull out something meaningful from it. 0-shot, no prompting.

- Event context: AI Tinkerers Seattle - February 2025 Meetup — 2025-02-22 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_7iT1m_WKor4

### [BAML (Community Demo Pit)](https://seattle.aitinkerers.org/talks/rsvp_Ss-fHhJS_u8)

Stop by the community demo pit to check out amazing demos from Boundary! - BAML is an open-source tool that transforms messy prompt templates into typed functions, making AI code easier to run and test. It offers a seamless experience for developers working with various AI models, simplifying the process of building AI pipelines without hiding prompts or proxying APIs.

- Event context: AI Tinkerers Summer Social - August 2024 — 2024-08-16 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_Ss-fHhJS_u8

## Related Technologies

- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [AI](https://aitinkerers.org/technologies/ai) ([Markdown](https://aitinkerers.org/technologies/ai.md)) — 55 public demos
- [AI pipelines](https://aitinkerers.org/technologies/ai-pipelines) ([Markdown](https://aitinkerers.org/technologies/ai-pipelines.md)) — 1 public demo
- [APIs](https://aitinkerers.org/technologies/apis) ([Markdown](https://aitinkerers.org/technologies/apis.md)) — 19 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [function calling](https://aitinkerers.org/technologies/function-calling) ([Markdown](https://aitinkerers.org/technologies/function-calling.md)) — 11 public demos
- [Image](https://aitinkerers.org/technologies/image) ([Markdown](https://aitinkerers.org/technologies/image.md)) — 4 public demos
- [Jina](https://aitinkerers.org/technologies/jina) ([Markdown](https://aitinkerers.org/technologies/jina.md)) — 1 public demo
- [JSON](https://aitinkerers.org/technologies/json) ([Markdown](https://aitinkerers.org/technologies/json.md)) — 20 public demos
- [LanceDB](https://aitinkerers.org/technologies/lancedb) ([Markdown](https://aitinkerers.org/technologies/lancedb.md)) — 5 public demos
- [LoRA](https://aitinkerers.org/technologies/lora) ([Markdown](https://aitinkerers.org/technologies/lora.md)) — 17 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
- [Neon](https://aitinkerers.org/technologies/neon) ([Markdown](https://aitinkerers.org/technologies/neon.md)) — 5 public demos
- [OpenRouter](https://aitinkerers.org/technologies/openrouter) ([Markdown](https://aitinkerers.org/technologies/openrouter.md)) — 34 public demos