Here's the updated README.md with the requested changes:
a weekly conversation about how we can all get the most juice out of todays models with @hellovai & @dexhorthy
📅 event calendar - https://lu.ma/baml
Discord - https://boundaryml.com/discord
every tuesday at 10 am pst on zoom.
1 hour of live code, q&a with some prepped content to help you take your ai app from a demo to production.
lets code together 🧑💻
to prevent repeating the basics, we recommend you come in having already understanding some of the tooling we will be using:
- zoom
- cursor (a vscode alternative)
- programming languages
- application logic: python or typescript or go (depends on session)
- prompting: baml
- repo: github.com/boundaryml/baml
- recommend getting started video
- package managers of choice:
- Python - UV
- Typescript - PNPM
| topic | description |
|---|---|
| 2025-07-29 #16: Evaluating Prompts Across Models RSVP |
AI That Works #16 will be a super-practical deep dive into real-world examples and techniques for evaluating a single prompt against multiple models. While this is a commonly heralded use case for Evals, e.g. "how do we know if the new model is better" / "how do we know if the new model breaks anything", there's not a ton of practical examples out there for real-world use cases. |
| 2025-07-22 #15: PDFs, Multimodality, Vision Models youtube • code • PAST |
Dive deep into practical PDF processing techniques for AI applications. We'll explore how to extract, parse, and leverage PDF content effectively in your AI workflows, tackling common challenges like layout preservation, table extraction, and multi-modal content handling. |
| 2025-07-15 #14 Implementing Decaying-Resolution Memory youtube • code • PAST |
Last week on #13, we did a conceptual deep dive on context engineering and memory - this week, we're going to jump right into the weeds and implement a version of Decaying-Resolution Memory that you can pick up and apply to your AI Agents today. For this episode, you'll probably want to check out episode #13 in the session listing to get caught up on DRM and why its worth building from scratch. |
| 2025-07-08 #13: Building AI with Memory & Context youtube • code • PAST |
How do we build agents that can remember past conversations and learn over time? We'll explore memory and context engineering techniques to create AI systems that maintain state across interactions. |
| 2025-07-01 #12: Boosting AI Output Quality youtube • code • PAST |
This week's session was a bit meta! We explored "Boosting AI Output Quality" by building the very AI pipeline that generated this email from our Zoom recording. The real breakthrough: separating extraction from polishing for high-quality AI generation. |
| 2025-06-24 #11: Building an AI Content Pipeline youtube • code • PAST |
Content creation involves a lot of manual work - uploading videos, sending emails, and other follow-up tasks that are easy to drop. We'll build an agent that integrates YouTube, email, GitHub and human-in-the-loop to fully automate the AI that Works content pipeline, handling all the repetitive work while maintaining quality. |
| 2025-06-17 #10: Entity Resolution: Extraction, Deduping, and Enriching youtube • code • PAST |
Disambiguating many ways of naming the same thing (companies, skills, etc.) - from entity extraction to resolution to deduping. We'll explore breaking problems into extraction → resolution → enrichment stages, scaling with two-stage designs, and building async workflows with human-in-loop patterns for production entity resolution systems. |
| 2025-06-10 #9: Cracking the Prompting Interview youtube • code • PAST |
Ready to level up your prompting skills? Join us for a deep dive into advanced prompting techniques that separate good prompt engineers from great ones. We'll cover systematic prompt design, testing tools / inner loops, and tackle real-world prompting challenges. Perfect prep for becoming a more effective AI engineer. |
| 2025-06-03 #8: Humans as Tools: Async Agents and Durable Execution youtube • code • PAST |
Agents are great, but for the most accuracy-sensitive scenarios, we some times want a human in the loop. Today we'll discuss techniques for how to make this possible. We'll dive deep into concepts from our 4/22 session on 12-factor agents and extend them to handle asynchronous operations where agents need to contact humans for help, feedback, or approvals across a variety of channels. |
| 2025-05-27 #7: 12-factor agents: selecting from thousands of MCP tools youtube • code • PAST |
MCP is only as great as your ability to pick the right tools. We'll dive into showing how to leverage MCP servers and accurately use the right ones when only a few have actually relevant tools. |
| 2025-05-20 #6: Policy to Prompt: Evaluating w/ the Enron Emails Dataset youtube • code • PAST |
one of the most common problems in AI engineering is looking at a set of policies / rules and evaluating evidence to determine if the rules were followed. In this session we'll explore turning policies into prompts and pipelines to evaluate which emails in the massive enron email dataset violated SEC and Sarbanes-Oxley regulations. |
| 2025-05-13 #5: evals evals evals youtube • code • RSVP |
stay tuned for our season 2 kickoff topic on minimalist and high-performance testing/evals for LLM applications |
| Break | We had a great time doing the first four episodes of AI that Works - we'll see y'all may 13th for season 2! |
| 2025-04-22 #4: twelve factor agents Youtube • code • PAST |
learn how to build production-ready AI agents using the twelve-factor methodology. we'll cover the core concepts and build a real agent from scratch. |
| 2025-04-15 #3: code generation with small models Youtube • code • PAST |
large models can do a lot, but so can small models. we'll discuss techniques for how to leverge extremely small models for generating diffs and making changes in complete codebases. |
| 2025-04-08 #2: reasoning models vs reasoning prompts youtube • code • PAST |
models can reason but you can also reason within a prompt. which technique wins out when and why? we'll find out by adding reasoning to a chat bot that generates complex cypher/sql queries. |
| 2025-03-31 #1: large scale classification youtube • code • PAST |
llms are great at classification from 5, 10, maybe even 50 categories. but how do we deal with situations when we have over 1000? perhaps its an ever changing list of categories? |