Systems | Development | Analytics | API | Testing

AI tools are getting smarter, and many of them now have access to more than you realize. From test scripts to config files to internal APIs, what starts as "just a helper" can become a hidden risk. In this AMA, Harinee will share where things go wrong when tools are trusted too quickly. We’ll look at real examples, permission pitfalls, and ways to keep your systems safer. If you’re using AI in testing or automation, this session will help you ask better questions. Bring your curiosity and your concerns. Let’s talk about what your tools can do, and what they shouldn't.

Getting support means reaching value and impact in days instead of weeks or months. Professional services bring proven expertise that accelerates adoption and makes teams the heroes, not the ones struggling to figure everything out alone. — Mush Honda, Chief Quality Architect at Katalon Follow Katalon for more insights in our series!

Agentic AI marks the next evolutionary leap in artificial intelligence - systems that don’t just answer prompts or generate content, but plan, decide, and act on our behalf with minimal oversight. In this webinar, we’ll demystify what “agentic” really means, trace the shift from single‑step chatbots to multi‑step autonomous agents, and explore the architectures—sense‑plan‑act loops, large‑language‑model reasoning layers, and tool‑integrations—that make true agency possible.

A quick overview of Xray Test Management - cutting-edge test management app for Jira. Xray is the leading Quality Assurance and Test Management app for Jira. More than 4.5 million testers, developers and QA managers trust Xray to manage 100+ million test cases each month. Xray is a mission-critical tool at over 5,000 companies in 70 countries, including 137 of the Global 500 like BMW, Samsung and Airbus.

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/