Systems | Development | Analytics | API | Testing

honeybadger

How to build a Copilot agent

Jan 26, 2026 By Joshua Wood In Honeybadger
A customer recently shared their debugging workflow with me. When an error shows up in Honeybadger, they import it to Linear, manually add context about where to look in the codebase, then assign GitHub Copilot to investigate. It works, but they asked a good question: could Copilot just access Honeybadger directly? The answer is yes—and it's easier than I expected.
Read Post

Build Agentic Workflows: Expose API Orchestration as MCP Tools with Kong AI Gateway

Jan 26, 2026 By Kong In Kong
Learn how to expose an API orchestration workflow as an MCP server using Kong AI Gateway, configure semantic guardrails, and build an agent with the Volcano SDK. We onboard GPT-4 behind /llm, orchestrate with DataKit, and debug MCP tools in Insomnia—end-to-end without adding server code.
View Video

Can We Still Trust the Code? #speedscale #qualityassurance #digitaltwin #trust #devops

Jan 26, 2026 By Speedscale In Speedscale
The "Velocity Gap" is real. AI like Claude and GitHub Copilot are pumping out code faster than ever, but there’s a catch: Engineers don't trust it yet. We’re moving away from the old days of "clicking around" in a test environment, but how do we verify code at the speed of light? Ken breaks down why the future of QA isn't just "testing," it’s simulation. Video collab with @ScottMooreConsultingLLC Learn More: speedscale.com.
View Video
kong

A Developer's Guide to MCP Servers: Bridging AI's Knowledge Gaps

Jan 26, 2026 By Adam DeHaven In Kong
Have you ever asked an AI assistant to generate code for a framework it doesn't quite understand? Maybe it produces something that looks right, but the syntax is slightly off, or it uses deprecated patterns. The AI is working hard, but it lacks the specific context it needs to truly help you. The Model Context Protocol (MCP) was designed to bridge this knowledge gap by giving AI assistants access to domain-specific knowledge and capabilities they don't have built in.
Read Post
ClearML

Multi-Node Training with ClearML

Jan 26, 2026 By ClearML In ClearML
Orchestrating distributed AI workloads Distributed (multi-node) training has become a requirement rather than an optimization for many modern AI workloads. As model sizes grow, datasets expand, and training timelines tighten, teams increasingly rely on multiple machines, often with multiple GPUs each, to complete training efficiently.
Read Post
Best 5 Tools for Monitoring AI-Generated Code in Production Environments

Best 5 Tools for Monitoring AI-Generated Code in Production Environments

Jan 25, 2026 By SystemsDigest In SystemsDigest
AI-generated code is no longer experimental. It is actively running in production environments across SaaS platforms, fintech systems, marketplaces, internal tools, and customer-facing applications. From AI copilots assisting developers to autonomous agents opening pull requests, the volume of machine-generated code entering production has increased dramatically. This shift has created a new operational challenge: how do you reliably monitor AI-generated code once it is live?
Read Post

Copyright © 2026 OpsMatters™. All rights reserved.