Systems | Development | Analytics | API | Testing

Learn more at speedscale.com or read more at https://speedscale.com/blog/peeking-under-the-hood-with-claude-code/

As AI becomes more capable, many managers assume that knowledge workers can be easily replaced by machines. Yet innovation still comes from people learning, collaborating, and sharing ideas. Rather than worrying about replacement, knowledge workers can actively demonstrate their value by developing strong public speaking skills.

Just like humans, AI systems are shaped by how they are brought up. In the case of Large Language Models, this upbringing happens through data collection, training, and productization. At each of these stages, bias can quietly enter the system through the data we select, the way models are trained, or the assumptions embedded into the final product. These biases, whether intentional or accidental, influence how models think, respond, and interact with users in the real world.

This talk explores the challenges of testing agentic AI systems—AI that autonomously reacts to events and initiates processes. Drawing on decades of experience, Robert Sabourin emphasizes that testing begins and ends with risk. A three-dimensional model (business impact, technical risk, autonomy) guides evaluation. Testers generate ideas using a broad taxonomy, from capabilities and failure modes to creative and adversarial approaches. Continuous testing and monitoring ensure findings inform business decisions, emphasizing learning over correctness.

As organizations rapidly adopt Large Language Models, many discover that building reliable and trustworthy AI systems is far more complex than traditional software development. LLMs are non-deterministic, context-sensitive, and prone to issues like bias, hallucinations, and prompt injection, making quality assurance a deeper challenge than simple testing.

Katalon’s AI approach is different because it builds on tools teams already use, adds AI without forcing process changes, and introduces novel capabilities like generating tests directly from real user behavior. It also applies AI across the entire testing lifecycle, creating a more complete and unified solution than most tools offer. — Coty Rosenblath, Chief Technology Officer at Katalon Follow Katalon for more insights in our series!

Testers are great at finding flaws in systems. But what happens when the system under test is the tester themselves? In today’s world of constant change, rising stress, and growing uncertainty, resilience has become just as critical as technical skill. From handling pushback and tight timelines to navigating burnout and self-doubt, testers face pressures that often go unseen.

AI promises speed, but testers are often the first to notice where it quietly breaks down. Beneath the impressive outputs lie hidden issues like hallucinations, false confidence, and blind spots that can easily go unnoticed yet cause real damage if left unchecked. This atomic talk explores the subtle ways AI can fail, why speed without reliability is risky, and how testers play a critical role in supervising and strengthening AI systems. It highlights practical strategies for working alongside AI to make its outputs more trustworthy, reliable, and genuinely useful.

Learn more: https://speedscale.com/