The text explores AI’s evolving role in QA/testing, outlining three AI integration levels (Assistant, Augmented, Agentic QE) and the PACT framework for agent design, emphasizing collaboration between human expertise and AI tools. It stresses retaining critical human skills, balancing automation with QA principles, and adapting through context-driven testing, open-source engagement, and strategic oversight of AI workflows.

How To Test This?

interview episodes where Mamadou N’diaye talks with with software testing experts

• https://podcasters.spotify.com/pod/show/spidey1944
• https://www.youtube.com/@HowToTestThis
• https://www.linkedin.com/in/mamadou-ndiaye-consultant/

Episode Details

• Show Notes: https://podcasters.spotify.com/pod/show/spidey1944/episodes/How-To-Test-As-Agentic-Quality-Engineer--Dragan-Spiridonov-e3hk7pk
• Published: 2026-04-08T17:12:53Z
• Duration: 00:38:26
• Author: Mamadou N’diaye

Overview

The podcast discusses the evolving role of artificial intelligence (AI) in quality assurance (QA) and testing, emphasizing the shift from traditional QA methods to agentic engineering. It outlines three levels of AI integration: AI Assistant QE, where AI supports tasks with human oversight; AI Augmented QE, where AI autonomously performs tasks like coding but requires supervision; and Agentic QE, where AI agents are fully orchestrated to handle complex software development lifecycle tasks. The PACT framework (Proactive, Autonomous, Collaborative, Targeted) is introduced as a structured approach to designing intelligent agents for testing, focusing on preemptive issue detection, minimal supervision, inter-agent collaboration, and goal-specific execution. Key challenges include avoiding unstructured “vibe coding” and ensuring AI is integrated with mature processes to avoid inefficiencies. Human skills like critical thinking, collaboration, and creativity remain essential, as AI complements rather than replaces QA expertise in risk assessment and exploratory testing.

The discussion also highlights the importance of foundational QA principles alongside AI adoption, such as validating agent outputs and aligning automation with business goals. Tools like Cloud Code and Rueflow are emphasized for managing agent workflows, with examples of open-source projects and AI-assisted testing platforms. Career advice encourages QA professionals to embrace AI as a tool for efficiency, develop context-driven testing skills, and engage in communities or open-source initiatives to stay relevant. The “10% rule” is proposed, advocating for 90% of time spent verifying AI outputs and only 10% instructing agents. Technical challenges like context drifting and over-engineering are addressed through task segmentation and progress-tracking systems. Overall, the content underscores the need for QA engineers to evolve into quality architects, leveraging AI for automation while maintaining ethical and strategic oversight of testing processes.

The podcast also touches on practical implementations, such as the Sentinel API project, which demonstrates agent-based testing of APIs, and the Agent QE Fleet, a custom-built set of AI agents for quality assurance tasks. Resources for learning, including blogs, online courses, and community engagement, are recommended to help QA professionals adapt to this new paradigm. The emphasis is on balancing AI’s capabilities with human judgment, ensuring that tools enhance, rather than replace, core QA competencies like exploratory testing, risk analysis, and critical thinking. The discussion concludes with encouragement to experiment with new technologies, build a strong portfolio of open-source projects, and stay engaged with the evolving field of QA engineering.

What If

• What if you adopt the 10% rule for AI agent training and verification in your QA workflow?
  Concrete move: Allocate 10% of your time (e.g., 1 hour daily) to train/adjust AI agents (like the Agent QE Fleet) and 90% to manually verify their outputs (e.g., test cases, logs, or code).
  Why now: The text emphasizes that AI agents require structured supervision, and over-reliance without validation risks inaccuracies. This balance ensures accountability while leveraging AIs efficiency.
  Expected upside: Reduced rework in QA cycles, faster task execution (e.g., requirements analysis or log parsing), and a more robust validation process to catch AI-generated errors early.

• What if you build an open-source QA tool using the PACT framework and AI agents?
  Concrete move: Replicate the Sentinel API Project by creating a GitHub repository for an agent-driven API test generator, using the PACT frameworks Proactive (preemptive issue detection) and Collaborative (agent-human feedback) principles.
  Why now: The text highlights the value of open-source contributions (e.g., Quantum Quality Engineerings work) and the need for structured AI integration (PACT). This aligns with community engagement and skill development.
  Expected upside: A ready-to-deploy tool for QA professionals, increased visibility in the QA community, and a tangible product to showcase in your portfolio.

• What if you integrate the “Four C’s” skills into your AI-agent workflows for QA?
  Concrete move: Design a process where agents act as “critical thinkers” (validate risks), “collaborators” (work with humans and other agents), “communicators” (generate clear test reports), and “creatives” (propose exploratory test scenarios).
  Why now: The text stresses that human skills like critical thinking and creativity are irreplaceable, even with AI. Embedding them into agent workflows ensures QA remains human-centric and risk-aware.
  Expected upside: More nuanced test strategies (e.g., identifying edge cases AI might miss), stronger alignment with business goals, and a competitive edge in QA leadership roles.

Takeaway

• Implement the 10% Rule for AI Agent Usage: Allocate 10% of your time to instruct AI agents and 90% to validate their outputs (e.g., verifying test cases, log analysis, or code suggestions) to ensure quality and accountability.
• Adopt the PACT Framework for AI Integration: Structure your testing processes using the Proactive (identify issues early) and Targeted (focus on specific objectives) components of the PACT framework to guide agent behavior and improve outcomes.
• Master the Four Cs of Human Skills: Develop Critical Thinking (analyze agent outputs), Collaboration (work with peers/agents), Communication (document and share agent workflows), and Creativity (design novel test scenarios) to complement AI tools.
• Set Up Agent QE Fleet for Automation: Use NPM and secure environments (e.g., CodeSpaces, Docker) to install Agent QE Fleet, leveraging its 60 agents and self-learning engine for tasks like API testing (via Sentinel API) or test case generation.
• Engage in Open-Source QA Communities: Contribute to open-source QA projects (e.g., Quantum Quality Engineering), join communities like the Ministry of Testing, and use GitHub to build and showcase agent-based tools in your portfolio.