Dmytro Kozlov
Dmytro Kozlov is a skilled software engineer with extensive experience in various roles within the technology and banking sectors. Currently serving as a Golang engineer at VictoriaMetrics since February 2022, Dmytro previously worked as a Full Stack Engineer at BrightLocal, focusing on building microservices in Golang. Prior to this, Dmytro gained expertise as a Front-end Developer at Luxoft and BrightLocal.com, utilizing technologies such as React and vanilla JavaScript. Dmytro's career also includes significant banking roles, with experience in sales management and key account management across several banks, where responsibilities included developing sales strategies and enhancing customer engagement. Dmytro holds a Specialist degree in Economics and Management from Dneprodzerzhinsk State Technical University.
Sessions
s observability systems grow more complex, the cognitive load on users increases quite fast. This talk presents an approach that could be game-changer in the future: using AI assistants as intelligent interfaces to your observability stack. By implementing and using MCP (Model Context Protocol) servers, we can transform how observability users interact with metrics, logs, and traces. You will see how teams can query their stack in plain English and use natural language to explore data, debug issues, and even work with configurations.
The session covers both theoretical foundations and practical implementation. It demonstrates how you can integrate AI assistants directly into your day-to-day workflows and provides a comprehensive walkthrough of:
- MCP architecture and how it enables LLMs (Large Language Models) to execute observability tasks
- Setting up and configuring MCP servers (demonstrated with VictoriaMetrics) and integration with popular AI assistants
- Current and planned features of VictoriaMetrics MCP Server
- Real-world use cases: data exploring, query explanation, working with alerting rules, cardinality analysis, intelligent debugging, obtaining context-rich answer for your questions, etc
- Various tips on how to make AI assistants work better with the observability stack
Whether you're an SRE looking to reduce toil, a platform engineer seeking to democratize monitoring access, or a leader evaluating AI's role in operations, this talk provides practical insights and tools for possible transformation of your observability practice.
This approach doesn't replace monitoring expertise at the moment — it amplifies it, making expert knowledge accessible to entire teams, giving you a powerful teammate in the form of AI assistant.
In cloud-native environments, understanding the behavior of distributed applications requires complete observability across metrics, logs, and traces. OpenTelemetry has become the standard for data collection, but it still depends on a backend capable of handling all three signals efficiently.
VictoriaMetrics, fully compatible with the Prometheus ecosystem, was designed to ingest and query large volumes of metrics with recognized performance and efficiency. Today, it extends these capabilities to logs and traces, enabling teams to centralize observability in a single open source system.
This session builds on the OpenTelemetry demo to show how signals are collected, stored, and correlated in VictoriaMetrics, then explored in Grafana. Attendees will see how this approach reduces operational complexity and provides a cloud-native, scalable observability stack without reliance on proprietary solutions.