Testers often need custom tools - data generators, mock services, internal dashboards, or CI helpers - but building them traditionally requires significant development effort and prioritization. With modern AI-assisted coding, we can now prototype and build these tools themselves, minimizing both engineering and maintenance efforts. In this session, I’ll show real examples of using vibe-coding to create internal testing workflows, interfaces, and CI/CD helpers. I’ll focus on where AI significantly accelerates development, where it introduces risks, and how to apply guardrails to keep these tools maintainable, secure and trustworthy.Rather than promoting “AI replaces engineers,” this talk presents AI as a practical productivity amplifier for experienced testers who understand their systems and constraints.
Key takeaways:- How to design and build tester-owned tools using vibe-coding without creating technical debtAttendees will learn how to approach AI-assisted development of internal testing tools (data generators, mock services, dashboards, CI helpers) with clear ownership boundaries, architectural decisions, and sustainability in mind.
- A realistic mental model for AI-assisted coding in testing workflowsParticipants will gain a clear understanding of where vibe-coding provides real leverage for experienced testers, where it breaks down, and how to critically evaluate AI-generated code instead of blindly trusting it.
- Practical guardrails for security, maintainability, and long-term useAttendees will leave with concrete strategies for applying constraints - such as validation, code structure, reviews, and documentation - to ensure AI-built tools remain trustworthy, auditable, and safe to evolve over time.