Sam Partee

Sam Partee

CTO + Co-founder

Sam is a pioneering engineer in AI. As Principal AI Engineer at Redis, Sam helped architect over 100 LLM-based apps for customers, making him among the world’s most experienced practitioners in real-world AI deployment. He led the AI engineering team that turned Redis’s vector database into their hottest product, proving he can turn bleeding-edge AI into actual revenue. He’s a major contributor to open-source AI projects like Langchain, LlamaIndex, Chapel, and DeterminedAI, giving him an even deeper insight into AI app challenges. His expertise spans from supercomputing - creating SmartSim at HPE to connect the world’s fastest supercomputers with ML infrastructure - to being the lead author on research on AI for climate science. Sam has built AI products and high-performance distributed systems and dug deep into AI theory. He knows LLM apps inside out - their limits, potential, and what developers need to make them work.

Articles (3)

All authors
Rays decoration
THOUGHT LEADERSHIP

The Day an AI Agent Merged Malicious Code (And What We Learned)

Yesterday started like any other day. Coffee, standup, code review. Then I heard about an incident that made me put down everything. An organization's AI agent had been compromised. Not through some exotic zero-day or sophisticated attack vector. No, this was far more elegant—and terrifying. Their LLM-powered browser agent had autonomously merged a malicious pull request on GitHub. As a real employee. With real permissions. The attack vector? A carefully crafted email sitting in the user's inb

Rays decoration
THOUGHT LEADERSHIP

We Need to Stop Calling RAG Systems 'Agents'

I'm going to say what everyone's thinking: if your system just searches documents and paraphrases results, it's not an agent. It's a search engine with a natural language interface. You've traded precision for generalization and gained the thrilling possibility of hallucinations. But there's no agency, no autonomy, no ability to actually do anything beyond return text that might not even be right. Don't get me wrong—I've built plenty of RAG systems. Hell, I've got a dozen still running in prod

PRODUCT RELEASE

LangChain Announces Open Agent Platform Powered by Arcade.dev

At the Interrupt Conference, LangChain unveiled a new agent platform that allows developers to build and share AI agents. The platform leverages Arcade.dev's support for Model Context Protocol (MCP) to enable agents to perform actions on behalf of users across hundreds of services. Why This Matters: * Complete Agent Ecosystem: Developers can now build, share, and deploy AI agents through an intuitive platform with flexible hosting options * Powerful Action Capabilities: Thanks to Arcade.dev

Blog CTA Icon

Get early access to Arcade, and start building now.

Sign up now
Docs