Last week, our team met in person for the Machine Learning Summit in Toronto where Dr. Greg and The Wiz presented the workshop RAG, Agents, and MCP: The 2025 Best-Practice Stack, and also gave us their first-hand insights into conference talks at the Summit - plus, get to meet our team!
This week, our team explored Meta’s Llama Stack, Llama Guard, and the many ways we can think about building with Guardrails in the Llama Ecosystem (called Llama Protections)! Of course, we built, shipped, and shared with RAG, Agents, and MCP as well!
🦙 LlamaIndex Agent Memory: From Short-Term Storage to Intelligent Retention
Tomorrow on Thursday June 25, join LlamaIndex DevRel Tuana Çelik and our very own Laura "The Legend" Funderburk as they unpack how the LlamaIndex memory component has evolved—from simple message history to advanced long-term memory systems powered by static content, extracted facts, and vector search. They'll discuss real-world use cases and explore how these memory blocks can transform agentic applications by allowing them to retain and use context across conversations.
This innovative application showcases the evolution of a playful retrieval experiment—matching LLMs with John Wick reviews—into a powerful 3-stage RAG evaluation pipeline. By integrating DeepWiki’s codebase exploration with the instruction-following precision of Claude Code, this prototype enables cost-effective, end-to-end evaluation of retrieval strategies with full observability and reproducibility. It's a breakthrough in AI-assisted development, blending rigorous experimentation with intuitive, AI-driven tooling.
Cohort 6 Highlight: Complimate by Pratik Murali — AI Assistant to reduce SaMD 510(k) Prep Time
Check out Complimate by Pratik Murali, an AI-powered regulatory bot that helps medical-technology teams compress the 6-24-month grind of compiling a water-tight 510(k) packages for class II software devices into, well, much faster timelines 📈.
We launched a full Cohort 7 of The AI Engineering Bootcamp on Tuesday - 70 students! Our team of instructors, course operations staff, and 10 peer supporters will work closely with each of them over the next 10 weeks to accelerate their building 🏗️, shipping 🚢, and sharing 🚀 of RAG, agent, and other end-to-end production-ready LLM applications (including some MCP servers, of course)! Applications are now open for Cohort 8 - secure your spot today!