TestCon Europe 2026
October 20-23
Vilnius & Online
Adam Sandman
About
Adam Sandman has been a programmer since the age of 10 and has worked in the IT industry for the past 25 years in areas such as architecture, agile development, testing, and project management. Currently, Adam is the Founder and CEO of Inflectra Corporation, where he is interested in technology, business, and enabling people to follow their passions.
At Inflectra, Adam has been responsible for researching tools, technologies, and processes in the software testing and quality assurance space.
Adam has previously spoken at STAR West, STAR East, Agile+DevOps conferences, STPCon, Swiss Testing Day, InflectraCon, TestingMind, EuroSTAR, Agile Testing Days, TestCon Europe, UNICOM, GSDC, and STAR Canada.
Adam Sandman | Don’t Be a Fool Mr. Bond: It Takes an Agent to Test an Agent
Just like MI5 uses agents to test and find other agents that have gone rogue, when it comes to AI, we need to use the same approach. In this talk I will discuss the limitations of how we are current testing AI agents, and why this means we are not adequately ensuring the safety of agentic AI systems. With non-deterministic systems like Generative/Agentic AI, we need to simulate a large number of inputs (millions) and measure the outputs using judge agents to find the statistical success rate. This a process that is more similar to how we traditionally do load testing rather than the simple functional testing we’re using with AI right now. I will explain how you can instead use tools like AgentCore to create orchestration agents that build other types of agent to make this new type of non-deterministic testing possible. If you want to be ready for the next wave of QA, this talk is for you.
Takeaways:
1. Current functional testing techniques are inadequate for testing agentic/generative AI systems
2. What does it mean to use LLM as Judge agents? What are input agents?
3. How can you create an AI testing orchestration pipeline for testing AI