This AI monitors itself and opens its own PRs

LangChain · Beginner ·🤖 AI Agents & Automation ·13h ago
Ramp built a self-monitoring loop that watches its own codebase, adds missing monitors, filters out noisy ones in shadow mode, and files bug fix PRs — before any engineer notices the problem. Alex Shevchenko walks through how it works and why so many of those PRs actually get merged. This clip is from Max Agency, a #podcast about how the best AI agents are actually being built. Hosted by Harrison Chase, CEO of LangChain, each episode goes deep with the builders designing, deploying, and learning from real agent systems in the wild. From architecture decisions to evals, tooling, and failure modes, Max Agency is for people who want to understand what it really takes to build useful agents.
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

Meta Crashed My Server to Train Their Ai. 110 People Said It Happened to Them Too.
Meta's AI training caused a server crash for one developer, with 110 others reporting similar experiences, highlighting the potential risks of AI development on external infrastructure
Medium · Startup
How Agentic AI Is Transforming Hiring in 2026
Discover how Agentic AI is revolutionizing the hiring process in 2026 and its potential impact on the industry
Medium · Startup
I Replaced My $60,000 Operations Budget With Three AI Systems. Here Is Exactly What I Did.
Learn how a solo founder replaced a $60,000 operations budget with three AI systems, and discover the exact steps taken to achieve this cost-saving feat
Medium · Startup
When AI Gets Stuck in Its Own Loop: The Autonomous Sunk-Cost Fallacy
Learn how AI can get stuck in its own loop due to the autonomous sunk-cost fallacy and why it matters for AI development
Medium · ChatGPT
Up next
How AI is Changing DevOps Engineering | Ex-Amazon Engineer reveals the secret | TrainWithShubham
GeeksforGeeks
Watch →