Skip to content
Sign in
Artwork for Software Testing Unleashed - QA, DevEx & Quality Engineering
Software Testing Unleashed - QA, DevEx & Quality Engineering · September 17 · 28 min

Agentic Systems in Testing: Why Humans Stay in the Loop - Nishan Portoyan

Nishan Portoyan on why 8 to 12 agents replace your entire test workflow What separates a handful of agents from a real agentic system? With Nishan Portoyan I talk about exactly that line, and why most teams are still on the wrong side of it. We walk through a full testing pipeline where eight to twelve agents handle everything from requirement review to performance test conversion, and I keep coming back to the question of where the human has to step in and why the AI simply cannot replace that judgment. Nishan is direct about what these systems cannot do: they do not think, they gather information and hand it back, and anyone expecting otherwise will run into trouble fast. "There is no intelligence in there. It's just gathering information and handing it over to you." - Nishan Portoyan Nishan Portoyan is a tester with a passion for his work. Whether it’s planning, coordination, automation, or execution, there’s no area of testing he doesn’t enjoy. Thanks to his solid training as a computer scientist and his degree in business administration, Nishan knows how to act professionally as a bridge between computer science and business. True to his motto, “If you love what you do, do it all the way or not at all,” he is deeply committed to the testing community in addition to his projects. Highlights: An agentic system is not a collection of individual agents given tasks by humans, but a goal-based ecosystem where agents orchestrate other agents autonomously. Between 8 and 12 specialized agents can cover the full testing process, from requirement review through test case creation, automation, and performance testing. AI cannot apply business rules or judge coverage the way humans do, so human oversight is not optional but structurally required at defined checkpoints throughout the agentic system. Performance test cases cannot be reused from functional automation because the scope differs fundamentally: functional tests control a GUI like a human, while performance tests examine back-and-forth system communication at scale. In data-protection-strict environments such as Switzerland, cloud-based AI tools like ChatGPT, Claude, and Gemini are not viable, and teams must run models such as Mistral or DeepSeek locally, for example via Ollama, on GPU-capable servers. 📘 Tool migration ahead? Teamscale playbook: migrate only 20% of tests, keep nearly all bug detection. Download for free

0:00-28:10
Play in
Transcript file

transcript

No transcript — this publisher did not publish one.

show notes

Nishan Portoyan on why 8 to 12 agents replace your entire test workflow

What separates a handful of agents from a real agentic system? With Nishan Portoyan I talk about exactly that line, and why most teams are still on the wrong side of it. We walk through a full testing pipeline where eight to twelve agents handle everything from requirement review to performance test conversion, and I keep coming back to the question of where the human has to step in and why the AI simply cannot replace that judgment. Nishan is direct about what these systems cannot do: they do not think, they gather information and hand it back, and anyone expecting otherwise will run into trouble fast.

"There is no intelligence in there. It's just gathering information and handing it over to you." - Nishan Portoyan

Nishan Portoyan is a tester with a passion for his work. Whether it’s planning, coordination, automation, or execution, there’s no area of testing he doesn’t enjoy. Thanks to his solid training as a computer scientist and his degree in business administration, Nishan knows how to act professionally as a bridge between computer science and business.

True to his motto, “If you love what you do, do it all the way or not at all,” he is deeply committed to the testing community in addition to his projects.

Highlights:

  • An agentic system is not a collection of individual agents given tasks by humans, but a goal-based ecosystem where agents orchestrate other agents autonomously.
  • Between 8 and 12 specialized agents can cover the full testing process, from requirement review through test case creation, automation, and performance testing.
  • AI cannot apply business rules or judge coverage the way humans do, so human oversight is not optional but structurally required at defined checkpoints throughout the agentic system.
  • Performance test cases cannot be reused from functional automation because the scope differs fundamentally: functional tests control a GUI like a human, while performance tests examine back-and-forth system communication at scale.
  • In data-protection-strict environments such as Switzerland, cloud-based AI tools like ChatGPT, Claude, and Gemini are not viable, and teams must run models such as Mistral or DeepSeek locally, for example via Ollama, on GPU-capable servers.

📘 Tool migration ahead? Teamscale playbook: migrate only 20% of tests, keep nearly all bug detection. Download for free

links2

more episodes

All episodes