AI Dev 26 x SF | Pratik Verma: Observability Agent to Find & Fix Issues in AI Agents

DeepLearningAI · Beginner ·🤖 AI Agents & Automation ·3h ago
AI agents fail in prod due to brittle workflows, a lack of contextual learning, and an inability to improve over time. At AI Dev 26 x San Francisco, Pratik Verma showed how to use trace-based testing with coding agents as part of agentic engineering to find and fix issues in AI agents. Attendees learned to debug, evaluate and observe AI agents using open source monocle2ai made easy with an observability agent.
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

⚡
Happycapy Review 2026: I Tested the Agent-Native Computer Pitch on a Real Workflow
Learn how to effectively utilize agent-native computer pitches in real workflows with Happycapy's tool
Medium · AI
 ⚡
Google’s AI Revolution Is Bigger Than Chatbots It’s the Beginning of the Autonomous Internet
Google's AI revolution is transforming the tech industry, marking the beginning of the autonomous internet, which will significantly impact various sectors
Medium · AI
 ⚡
Governance and Security in Agentic Pipelines: Regulated Environments + AI
Learn to implement Policy-as-Code and Agent-as-Auditor patterns for secure agentic pipelines in regulated environments with AI
Medium · DevOps
 ⚡
The $100K Service Is Now a $4K AI Product. Is Your Firm Next?
Learn how AI can transform high-cost services into low-cost products, and assess your firm's operational maturity to stay ahead
Medium · AI
Up next
Multi-Agent Systems & Workflow Orchestration: Why Solo Agents Fail to Scale
Data Science Dojo
Watch →