AI & LLMs

30 to 70 PRs a Day: How We Managed to Not Wreck Our Systems

July 16, 2026

30 to 70 PRs a Day: How We Managed to Not Wreck Our Systems

The Honeycomb engineering team set out to double our productivity in a year. This is how we did it, what we did to keep things stable, what it cost us, and what we’re still figuring out.

AI & LLMs

Software Engineering

AI Amplifies Your Existing Practices: Lessons from Our Shift to an AI-First Strategy

July 16, 2026

Liz Fong-Jones

AI Amplifies Your Existing Practices: Lessons from Our Shift to an AI-First Strategy

As the Honeycomb engineering team worked to double our productivity, we learned a lot. The most important takeaway? Nothing anyone tells you about AI will land if your starting substrate is unhealthy.

AI & LLMs

Software Engineering

Shipping Is Your Company's Heartbeat: A Letter from a CTO

July 14, 2026

Charity Majors

Shipping Is Your Company's Heartbeat: A Letter from a CTO

In an open letter to engineering leaders everywhere, Fin CTO Darragh Curran explains that AI isn't a magic wand but rather an amplifier—of the good and the bad—of your engineering practices. And engineering rigor is more important than ever.

July 13, 2026

Lattice Watch: Smarter Guardrails for Design System Observability

In the past, I was part of a group of engineers responsible for doing random code reviews with an eye for design system adherence. The design system team had been tracking who used their system the most and invited those engineers to help them review PRs, with the hope that education would be the key to getting more product engineers to use the system. I wanted to create something like that here at Honeycomb for our design system, Lattice.

July 8, 2026

Multi-Agent Collaboration on a Shared Canvas

This is part 2 of a series on taking agentic applications from prototype to production with AWS AgentCore. Part 1 covers foundational design questions, like cardinality, session lifecycle, state management, and operational constraints. This post goes deeper on one of those topics: how we use the difference between an LLM session and an AgentCore Runtime session to build collaborative multi-agent investigations.

AI & LLMs

Dogfooding

From Prototype to Production With AWS AgentCore

July 6, 2026

Moses Mendoza

From Prototype to Production With AWS AgentCore

Canvas runs on AWS Bedrock AgentCore. We picked AgentCore because it supports the ramp described in this post: it’s quick to get running, it’s modular, and it has production-grade underpinnings. But, like any platform, it has some traps to be aware of. In this post, we share some of the most important things we learned while building on AWS AgentCore.

AI & LLMs

What Customers Are Doing With AI and Honeycomb

June 30, 2026

Rox Williams

What Customers Are Doing With AI and Honeycomb

At O11yCon, we talked to engineering teams across the industry, and the numbers are starting to get genuinely wild: Mixpanel DevOps Engineer Eddie Bracho told us their engineering team is generating 50% more PRs than before AI came into the mix (sorry).

O11yCon

Conferences & Meetups

AI & LLMs

How to instrument AI agents for Honeycomb's Agent Timeline

June 29, 2026

Dan Juengst

Instrumenting AI Agents for the Agent Timeline: A Practical OpenTelemetry Guide

The LLM is rarely the root cause of agent failures. This technical guide shows how to instrument AI agents using OpenTelemetry's GenAI semantic conventions so they appear in Honeycomb's Agent Timeline—including tool calls, multi-agent handoffs, and framework-specific SDKs—so you can debug what actually went wrong.

June 18, 2026

Agent Timeline Is Now Generally Available

Honeycomb’s Agent Timeline gives you a unified view of LLM behavior and multi-agent workflows, so you can investigate entire conversations and quickly see where prompts, tool calls, and failures happened, in the order they happened.

Product Updates

AI & LLMs

June 15, 2026

Colin Burke

Observability: Are You Measuring What Actually Matters?

Old observability metrics like uptime and MTTR aren't enough anymore. Teams must connect technical signals to business outcomes, especially as AI raises the stakes.

June 8, 2026

It Can Only Goodhart Happen

Is the era of tokenmaxxing over before it even began? The rise of token leaderboards and the death of token leaderboards at companies like Amazon seem to have taken place in less than three months!

AI & LLMs

Honeycomb Canvas: The Multiplayer Workspace for the Agentic Era

May 20, 2026

Kale Bogdanovs

Honeycomb Canvas: The Multiplayer Workspace for the Agentic Era

Auto-investigations that start the moment a trigger fires. Custom skills that encode your team's runbooks. A live workspace where humans and agents investigate production together. Now available to all Honeycomb customers.

May 19, 2026

Agent Timeline: The Flight Recorder for Your AI Agents

Every LLM call, every tool invocation, every agent handoff, every downstream service span, in one conversation, in one view. Now in Early Access.

May 13, 2026

Innovation Week Day 2: Observability for AI, and Observability With AI

AI is reshaping the SDLC in two directions at once. AI-generated code is shipping faster and with less human supervision than ever before, while agents and LLMs are running directly in production, where they behave very differently from traditional software: non-deterministic, with a wider blast radius than any single function or component, with no stack trace to catch when something goes wrong.

Innovation Week

AI & LLMs

May 12, 2026

Shabih Syed

Innovation Week Day 1: The SDLC Is Collapsing, and Observability Has Never Mattered More

Day 1 of Innovation Week was about how software gets validated, where observability fits, and the problems that have always been hard but are now genuinely urgent with AI part of the software development lifecycle.

Innovation Week

AI & LLMs

Making Semantic Conventions Work for You With OpenTelemetry Weaver

May 11, 2026

Mike Goldsmith

Making Semantic Conventions Work for You With OpenTelemetry Weaver

In this post, I'll show how OpenTelemetry Weaver lets you define, layer, and validate semantic convention schemas so that both humans and agents have full context on every attribute in your telemetry.

April 29, 2026

New in the Honeycomb Academy: Learn to Use the Honeycomb MCP

The new Honeycomb MCP course in the Honeycomb Academy gives you a starting point when you're not sure what to ask, and teaches you how to direct an investigation so you're getting evidence, not just answers.

AI & LLMs

April 27, 2026

Austin Parker

Approaching the Parhelion

A parhelion is created when light refracts through hexagonal ice crystals in the atmosphere, forming bright spots that appear on the horizon, connected by a faint halo. You don’t have to squint very hard to appreciate how relevant this is to our current AI moment.

AI & LLMs

Fast AI Feedback Loops with Honeycomb and OpenTelemetry

April 20, 2026

Ken Rimple

Fast AI Feedback Loops with Honeycomb and OpenTelemetry

Observability is the visibility you need to get the job done. Sending telemetry to Honeycomb explains what your agents are actually doing. OpenTelemetry provides semantic conventions for generative AI systems, a spec that defines how agents, LLMs, MCPs, and tools are properly observed. The primary telemetry is defined as trace spans and other events with specific naming patterns, mostly starting with gen_ai.

AI & LLMs

OpenTelemetry

ICYMI: Is This Code Worth Running? Here’s How to Know

April 14, 2026

Rox Williams

ICYMI: Is This Code Worth Running? Here’s How to Know

Over the last three months, we’ve been exploring what about software development and observability changes with AI, and what doesn’t. Our conclusion: these five principles will still remain true, even when 90% of the code is AI-driven.

AI & LLMs