Operations | Monitoring | ITSM | DevOps | Cloud

This blog is based on a presentation by Guillaume Moigneu at the Symfony 2024 conference. Machine learning and AI are no longer limited to Python and Node.js. PHP developers can now run AI models directly in their applications using modern tools and libraries. This guide shows you how to implement machine learning inference in PHP using ONNX and Transformers.

Multi-agent AI systems are trending in the software development industry right now. These systems consist of a group of individual agents that collaborate to achieve a desired goal. They mimic real world teams and departments in how they are organized. In multi-agent AI systems, each agent is assigned a task that is required to achieve a final output.

Engineering leaders face a constant barrage of questions that pull them away from strategic work. A team lead asks about scorecard compliance. A PM wants a status update on a migration. Someone needs incident trend data for a quarterly review. Each question is reasonable. Each requires context switching, digging through dashboards, or pinging someone on your team for a report. What if you could just ask?

When we introduced Canvas in beta, our goal was to reimagine how teams explore and collaborate around their observability data without requiring manual querying. Canvas has quickly become the AI-guided workspace that helps teams transform raw telemetry into meaningful, shared understanding faster than ever before. And today, we’re thrilled to announce that Canvas is now Generally Available (GA) for all Honeycomb users.

Recently I've been to Lisbon's Web Summit conference, a 3 day, 70,000 participants, 15 stages, 800+ speakers event. Even though there was a track called "AI Summit", all the talks were about AI and AI Agents and how the future of the web, business, economy is more and more AI, and how businesses and people should take steps to adapt as soon as possible to an online world managed and operated by Artificial Intelligence.

Everyone wants to move faster with AI, but few are truly ready for it. This is where organizations can position themselves better as AI readiness isn’t just about algorithms, it’s about whether your data, systems, and teams are prepared to support intelligent automation safely and effectively.

Life is pretty good. I’ve shipped a mobile app and I’m (happily) drowning in telemetry. Battery impact, time in foreground/background per screen, crash rates, slow frames, network retries – the works. The data is brilliant; the challenge is turning signals into reliable alerts that catch real issues which are relevant to my app’s functions. So… what should I actually listen for, and where should I set the thresholds?