Operations | Monitoring | ITSM | DevOps | Cloud

In Part 1 of this series, we explored how to instrument a LangChain trip planner agent with OpenTelemetry and send telemetry data to SigNoz. By tracing each step of the planning process: LLM reasoning, tool calls for flights, hotels, weather, and activities, and the final itinerary response, we saw how observability turns a black-box agent workflow into a transparent, debuggable system.

LangChain has become one of the most popular frameworks for building LLM-powered applications, making it easier to create agents that can reason, plan, and take actions. But like any production-grade AI app, LangChain agents can run into performance bottlenecks, hallucinations, or tool call failures. And without proper LangChain observability, it’s hard to know where things break down.

As you develop internal tools or public-facing data applications, implementing authentication mechanisms becomes essential. Without authentication, you risk exposing sensitive information or allowing unauthorized access. Fortunately, integrating secure user access does not have to be complex. AWS Cognito provides a straightforward way to handle authentication, user management, and access control across multiple identity providers.

Monitoring your websites from the US region is critical for serving users from the US as it helps you improve website performance and compliance-related practices, ensure business continuity, and offer a better customer experience. Just a few milliseconds of added lag specific to US connections can impact bounce rates and conversions, making localized monitoring essential.

APAC customers have high expectations around instant payments, open banking, and mobile-first experiences. In March 2025, India’s real-time payment system, UPI went down for five hours. Millions experienced payment failures, failed fund transfers, and login errors and many vented their frustrations on social media. With banking and payment disruptions on the rise, regulators are calling for proof of resilience.

When incidents strike, your on-call engineer jumps in first. They assess the issue, triage it, and try to resolve it. But sometimes, they can’t solve the problem or aren’t available. That’s when escalation policies step in to find the right backup. In this guide, I’ve explained how escalation policies work, why every team needs them, and how you can set up one. Also, I’ve included ready-to-use templates to help you get started fast.

Today, we are going to take a look at the Icinga 2 API and the various ways targets can be specified for different actions, such as querying information or scheduling downtimes. This post focuses on the API request payloads themselves and assumes some familiarity with sending requests to the Icinga 2 API. Please refer to our documentation for the missing details if you want to try the requests yourself. In general, specifying the objects to which an action applies works the same way for all actions.