In partnership with

Tech Transformed video podcast 34 min

Can Your Observability Stack Handle 24/7 Agentic Query Volume?

Eric Tschetter, Chief Architect at Imply, joins Kevin Petrie to explore why AI agents, with their continuous 24/7 query patterns, are breaking traditional observability tools.

Guest Eric Tschetter Chief Architect at Imply
Host Kevin Petrie Vice President of Research at BARC

In this episode

  • Why agents change query economicsContinuous AI workloads place sustained pressure on storage, compute and query performance.
  • How to break down data silosStore data once and let multiple teams and tools access it in the ways they already work.
  • Where security and observability overlapSRE, security and business teams often need the same underlying data across different time horizons.
  • What an observability warehouse doesA decoupled data layer that supports SPL, KQL, CQL, LogQL and other familiar query workflows.
Watch now — unlock the full episode

About the episode

The real challenge is within the data infrastructure

With enterprises rushing to integrate AI agents into operations and security, attention often focuses on the AI model itself. Eric Tschetter, Chief Architect at Imply, argues that the deeper challenge sits in the data infrastructure supporting those systems.

Unlike human analysts, AI systems work continuously. They produce much higher query volumes and put greater pressure on the platforms underneath. Modern observability architectures therefore need to manage more data, more users and more machine-to-machine interactions without losing speed.

For Tschetter, the answer is not another observability tool. It is a rethink of the data layer that supports the tools teams already use.

What you will learn

A practical discussion for observability, security and data leaders

01

Why agents change query economics

AI agents issue more queries than human analysts and can place sustained pressure on storage, compute and query performance.

02

How to break down data silos

Explore the case for storing data once and allowing multiple teams and tools to access it in the ways they already work.

03

Where security and observability overlap

See why SRE, security and business teams often need the same underlying data, even when their tools and time horizons differ.

04

What an observability warehouse does

Learn how a decoupled data layer can support SPL, KQL, CQL, LogQL and other familiar query workflows over shared data.

Inside the conversation

Six focused chapters across the 34-minute episode

The discussion moves from the immediate impact of AI agents to architecture, team collaboration and a shared data foundation.

  1. Introduction to AI and observability
  2. Challenges in observability with AI
  3. Modernising architecture for observability
  4. Decoupled observability and semantic layers
  5. Collaboration between IT and security teams
  6. Imply's observability warehouse and data lakes

The executive takeaway

What you really want is the data stored once and to access it from multiple different places.

The episode examines why connecting silos is not the same as removing them, and why CIOs, CISOs and data leaders need a shared, scalable foundation for observability, security and AI workloads.

In partnership with

Imply, the Data Layer for Observability, Security, and AI, empowers organizations to keep more data, search it faster, and spend less without changing their tools. Founded by the original creators of Apache Druid®, Imply delivers cloud-native infrastructure trusted by leading enterprises worldwide.