honeycomb.io

LLM apps are powerful, but they're also hard to debug and expensive to run. Observability shouldn't make that worse. In our latest blog, we break down how the Python OpenTelemetry SDK impacts performance in LLM workloads and what happens when you rethink the stack. If you're building with LLMs and care about performance, this is worth a read 👉 https://lnkd.in/e_aHurKw #honeycomb #OpenTelemetry #AI #LLMs

We’ve spent a lot of time talking about what it means to be fast, deep, and ready in observability. But as systems grow more complex and the pace of change continues to accelerate, those fundamentals are just the starting point. The real question is how teams build on them to keep up with what’s next. This blog takes a closer look at where things are heading and how teams can evolve their approach to meet the moment. Read more 👉 https://lnkd.in/ePVjMmCA #honeycomb #observability #AI #LLMs

We’re so excited for all of our incredible speakers at #O11yCon, May 20–21! Jody Bailey, Chief Product and Technology Officer at Stack Overflow, will explore how AI agents change the way we think about organizational knowledge in production. As agents take on more implementation work, gaps in context and outdated decisions become real risks. Jody will dive into why knowledge trust scoring—provenance, recency, and reliability—is becoming critical. You don't wanna miss it 👉 https://go.hny.co/47QIR4v

We recently hosted a webinar with Austin Parker and Akshay Utture (Augment Code), and you all brought some great questions—more than we could answer live. We followed up with a blog covering topics like trust, drift, and production feedback for AI agents. Read more 👉 https://lnkd.in/eAuACxRG #honeycomb #observability #AI #LLMs

We’re so excited for our #O11yCon lineup this year! Hear from Nathen Harvey (Google), Corey Quinn (Duckbill), Boris Tane (Coreplane Labs), David Poll (GitHub), plus Christine Yen, Charity Majors, Jessica Kerr, and more. Stay tuned for potential updates! 👀 May 20-21 · San Francisco 👉 https://go.hny.co/47QIR4v

AI coding tools are normalizing production behaviors that used to be unthinkable. Charity Majors, co-founder & CTO of honeycomb.io, has sharp opinions on what that means and what observability looks like when agents are shipping to prod. She's joining our Agent-Led Trust & Safety panel at Write-Only Code Summit on May 7. Use code COMMUNITY for 20% off: https://lnkd.in/gPk_Fgg3

AI agents are starting to work directly with production data, investigating issues, following traces, and surfacing what’s happening in real systems. This post explores how MCP and Canvas support that workflow by connecting context and action. Read more 👉 https://lnkd.in/eMd2ki56

In case you missed it: #O11yCon 2026 is coming to San Francisco, May 20-21. 🐝 AI agents are shipping code, triaging incidents, and making decisions in your production systems right now. Most teams still can't tell you what those agents actually did—or whether it went well. Observability closes that gap. O11yCon is where we talk about how. Here's what to expect: 📅 Day 1: Hands-on workshops with Amazon Web Services (AWS), Cribl, Embrace, and more 🎤 Day 2: Parallel practitioner and leadership tracks 🗣️ Speakers from Google, Salesforce, Stripe, GitHub, Stack Overflow, and more 🎟️ Early bird tickets: $99 until April 28 (then $199) Read the full announcement and register 👉 https://lnkd.in/ejaAMkEs

If you’re attending AWS Summit London, be sure to stop by Colin Burke and Romain B.’s session: “Shipping 100 Changes a Day: Observing an AI Agent at Scale.” Learn how Honeycomb + Intercom introduced a customer‑centric “time to first token” metric, rebuilt distributed tracing, and used SLOs to cut latency by 60% while 20 teams ship ~100 changes/day. Don’t miss it 👉 https://lnkd.in/ek9yWeHw