Agent Under the Microscope: Monitoring Agentic Workflows with OpenSearch

AI agents are moving from demos to production, but observability hasn't kept up. When an agent takes a wrong path, hallucinates mid-task, or silently degrades, how do you investigate? Traditional APM treats agent execution as a black box. We need purpose-built, OpenTelemetry-native observability for agentic AI.

We introduce the Agent Traces and Agent Health for OpenSearch: a native UI for exploring agent execution traces. OTel SDKs with GenAI semantic conventions (gen_ai.* attributes) instrument your agents, Data Prepper ingests the spans, and Agent Traces show you hierarchical trace views, detail agent maps, and aggregate metrics like token usage and latency percentiles - all queryable via PPL.

We demonstrate root-cause investigation: expanding execution trees to inspect each LLM call and tool invocation, querying spans to answer "which tool call caused the agent to diverge?" We then go deeper with Agent Health's golden path comparison that evaluates trajectories against expected behavior. Whether you're building agents for customer support, code generation, or data pipelines, you'll leave with a practical playbook for agent observability.

From Queries to Insights: AI-Powered Database Monitoring with OpenSearch and Prometheus

Databases are the backbone of every application, yet monitoring them effectively remains a challenge. In this session, we walk through monitoring production databases powering an e-commerce platform Valkey for caching and PostgreSQL for the catalog deployed on Kubernetes & Docker, using OpenSearch and Prometheus as the observability backbone.

We demonstrate a complete OpenTelemetry-based pipeline: instrumenting both databases with OTel SDKs, routing telemetry through Data Prepper to store time-series metrics in Prometheus and traces/logs in OpenSearch. With AI-assisted investigation using text-to-PPL and text-to-PromQL, engineers query live telemetry in natural language asking "show me slow queries in the catalog service in the last hour" without writing complex syntax.

We also show how to use AI to generate RCA visualizations and surface performance insights across your database fleet. Whether you manage a handful of databases or hundreds, you'll leave with practical patterns for building an OpenTelemetry-native database observability stack.

From Kernel to Cloud: Building a Complete Open Source Observability Pipeline

Modern cloud-native environments demand comprehensive observability, but achieving this without vendor lock-in remains challenging. This session demonstrates a new approach to full-stack observability using an entirely open source architecture. Through a live demonstration, we'll showcase how eBPF-based instrumentation via Inspektor Gadget can seamlessly capture deep system telemetry from Kubernetes environments, which is then unified and processed through OpenTelemetry Collector, and ultimately analyzed using OpenSearch and Prometheus ( Cortex ).

The presentation will reveal how this powerful combination enables unified visualization of metrics, logs, and traces without proprietary solutions. Attendees will witness practical implementations of cutting-edge features, including OpenSearch's new Prometheus metrics support and PromQL integration, while learning essential configuration steps and real-world troubleshooting techniques.

Whether you're an SRE, platform engineer, or technical architect, you'll leave with actionable insights for deploying these tools in your own environment.

Presented at OpenSearch Con NA, San Jose, 2025

https://opensearchconna2025.sched.com/event/25Gp0/from-kernel-to-cloud-building-a-complete-open-source-observability-pipeline-anirudha-jadhav-shenoy-pratik-gurudatt-amazon-web-services

OpenSearch: The Open Source Path to Search and Observability

OpenSearch has become a cornerstone of open source search and observability, empowering developers and organizations to derive meaningful insights from unstructured data at scale. With OpenSearch officially joining The Linux Foundation in 2024, backed by tech giants such as IBM, SAP, Uber and AWS, it further cemented its position in the open source ecosystem.

In this session we’ll introduce OpenSearch, from indexing and analyzing unstructured logs to full observability capabilities across tracing, monitoring and security. We’ll share latest improvements in query performance and scalability, and real-time analytics, as well as its expanding ecosystem with new plugins and SDKs in multiple programming languages, and its compatibility with cloud-native environments. You’ll even find vector search and natural language processing capabilities for your AI/ML development.

Presented at Scale 23x, Pasadena 2026.
https://www.socallinuxexpo.org/scale/23x/presentations/opensearch-open-source-path-search-and-observability