Operations | Monitoring | ITSM | DevOps | Cloud

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.

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.

If you’ve ever worked in a loud office, you know the drill: A co-worker’s on a call, someone’s talking about the next Taylor Swift album in the break room, another’s constantly clearing their throat, and the HVAC sounds like a jet engine. It’s loud. Your brain tries to filter it all out, but it’s no use. Then you put on noise-canceling headphones… and suddenly, you can think again.

If you're like me, you got into this business because you love building awesome apps. If you've been in the development space long enough, you'll eventually have to do work on those awesome apps that doesn't feel so awesome. Security can be one of those things. Taking Rails security seriously is important, even though the Rails framework does much of the heavy lifting. Before we get too deep into the details of Ruby on Rails security, let's take a second to reflect on the good times. ...

The Elasticsearch storage engine team has made significant strides in improving storage efficiency and performance in Elasticsearch 8.19 and 9.1. Now that these changes are available, what impact can they have on your business? And how do you make the most of them?

Imagine you’re a frontend engineer monitoring the user experience for an e-commerce app. You notice your checkout flow has a 15% abandonment rate. Your API responses are inconsistent. Your users are frustrated, and you’re drowning in data and complex queries trying to figure out why. Sound familiar? You can use real user monitoring (RUM) to determine what has happened, looking at page load times, error counts, user sessions, etc.

Today, we’re releasing InfluxDB 3.4 for Core and Enterprise, as well as our 1.2 update for the Explorer UI. This release focuses on developer efficiency, operational automation, and targeted security enhancements, giving teams faster setup, smoother workflows, and stronger guardrails for production use. InfluxDB 3 Core is free and open source, optimized for recent data, and licensed under MIT and Apache 2.