Scaling AI Observability: Handling Complex Agent Data
AI systems require robust observability for reliability and performance. The volume and complexity of multimodal data present significant challenges for traditional monitoring. This session explores how to use timeline correlations to perform root cause analysis on traces, embeddings, metadata, and raw blobs. It also demonstrates how LanceDB’s architecture enables real-time analysis and efficient root cause analysis for complex agent logs. 𝐊𝐞𝐲 𝐓𝐚𝐤𝐞𝐚𝐰𝐚𝐲𝐬: • Why traditional monitoring fails for multimodal AI data • Using timeline correlations to find the source of bad results • How to perform efficient root cause analysis on raw blobs and embeddings Subscribe to our calendar: https://luma.com/AgenticAIObservability

▶︎
Transformers, the tech behind LLMs | Deep Learning Chapter 5

▶︎
Data+AI World Tour for Government 2025 -Measuring Mission Impact

▶︎
SAIC #033 - Secure AI Agent Use Cases in Entreprise Environments

▶︎
Building Trustworthy, High-Quality AI Agents with MLflow
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hq720.jpg?sqp=-oaymwEbCNAFEJQDSFryq4qpAw0IARUAAIhCGAG4AvcY&rs=AOn4CLBvMdKvkZHL9Earmgc5OX3Iuc1UUQ&usqp=CCc)
▶︎
Yann LeCun's $1B Bet Against LLMs [Part 1]

▶︎
Debugging Multi-Agent Systems: Tracing Cascading Failures

▶︎
How to Build Systems to Actually Achieve Your Goals

▶︎
Exposing The Solid State Donut Battery. It's Over.

▶︎
Effective AI Agent Evals: Beyond Manual Review

▶︎
The Open Source community is collapsing

▶︎
Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

▶︎
But what is quantum computing? (Grover's Algorithm)

▶︎
Andrew Ng: Building Faster with AI

▶︎
Don't learn AI Agents without Learning these Fundamentals

▶︎
Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

▶︎
Building Self-Healing Agents: Automating the Feedback Loop

▶︎
Learn 97% of Claude in Under 16 Minutes

▶︎
What AI Agent Skills Are and How They Work

▶︎
RAG Crash Course for Beginners

▶︎
