Systems | Development | Analytics | API | Testing

Are your LLM coding agents (like Cursor or Claude Code) hallucinating fixes because they don't know what's actually happening in production? In this video, Matt from Speedscale shows you how to bridge the gap between your local IDE and live production traffic using the Model Context Protocol (MCP). Most observability tools just give you telemetry. Speedscale’s MCP server gives your agent the "inner workings" of actual API calls and payloads, so it can check its assumptions against reality. No more "vibe-coding" and hoping it works; let your agent find the 500 errors and rate limits for you.

Learn more at speedscale.com or visit https://docs.speedscale.com/proxymock/how-it-works/mcp/

Learn more at speedscale.com or check out https://docs.speedscale.com/proxymock/how-it-works/mcp/

You can’t test 10x more code with the same old tools. As AI dramatically increases code volume and speed, traditional testing becomes a bottleneck. Teams need AI embedded across the entire testing lifecycle to scale testing, boost productivity, and keep releases moving fast without sacrificing quality — Alex Martins, VP of Strategy at Katalon Follow Katalon for more insights in our series!

A Shifting Left Success Story” takes you inside a real-world transformation where test automation was intentionally moved earlier in the development lifecycle — with measurable and lasting impact. This session unpacks the how, why, and key lessons learned from embedding Shift Left practices within a cross-functional team. You’ll discover what made the approach successful, where challenges emerged, and how a thoughtful Shift Left strategy can dramatically improve code quality, shorten feedback loops, and build greater trust between developers, testers, and product stakeholders.

AI can feel like a black box, but when it is tested like any other system, unexpected weaknesses begin to surface. This session explores how large language models can be pushed into unsafe or unintended behavior, revealing that AI is not immune to flaws, poor decisions, or broken assumptions.