AutomationSTAR

Test Automation Conference Europe

Track Talk W1

Quality Model for Agentic SDLC

Szilard Szell

14:40-15:25 CET, Wednesday 4th November

Did you hear that, “An AI-powered coding tool wiped out a software company’s database, then apologized for a ‘catastrophic failure on my part’”?

In recent months, real-world examples have underscored the limits and risks of AI-generated code. In one widely publicised incident, an autonomous AI coding assistant on a development platform deleted an entire company’s live production database despite explicit instructions to freeze changes, then fabricated false data and obscured its own errors before the issue was corrected.

These incidents are not outliers; they reflect a deeper challenge arising when AI systems write and modify code autonomously — developers and quality engineers can no longer assume deterministic behavior, clear oracles, or safe outputs.

In this talk, we explore how automation engineers can level up by shifting from tool-centric automation to strategic quality engineering in AI-augmented delivery pipelines. Rather than competing with AI, we focus on human-AI collaboration: knowing when to trust AI outputs, when to challenge them, and how to design automation and quality practices that remain reliable in a non-deterministic, agent-driven world.

Building on my previously presented Three-Pillar Balanced Quality Model (Proactive, Detective, Reactive), the session shows how to design an agentic SDLC architecture that covers all autonomy levels (L1–L4) — from AI suggestions in IDEs to agents capable of merging changes into production.

The talk emphasizes skills AI cannot replace: critical thinking, risk assessment, quality strategy designed as part of the CI/CD pipeline, and communication. Attendees will see how automation engineers evolve into quality governors and AI supervisors, using AI to accelerate delivery while retaining human judgment over correctness, safety, and business value.

This session is aimed at automation engineers who want to future-proof their careers by adapting their craft — not abandoning it — and by building automation and quality practices that thrive in AI-infused software systems.

BACK TO PROGRAMME

What you will Learn

  1. Designing context-rich automation and intent-driven tests that guide AI rather than blindly validating its output
  2. Applying high-signal validation techniques (property-based, mutation, adversarial testing) to assess AI-generated code and tests
  3. Leveraging observability, telemetry, and production feedback to validate behavior when deterministic oracles no longer exist

Session Details

  • Intermediate
  • 30 minutes
  • 15mins Q&A
  • Automation Strategy & Architecture
Buy Conference Ticket

Check out this video from Szilard Szell on this talk Quality Model for Agnetic SDLC. We look forward to welcoming you to AutomationSTAR 2026.

Session Speaker

Szilard Szell

Eficode, Finland

Public speaker, coach, and teacher Szilárd Széll is a DevOps and AI Transformation Lead, Test Coach, and SAFe 6.0 SPC at Eficode. He has years of experience with DevOps transformation, especially in the telco industry now focusing on AI agentic SDLC. He has also worked as an assessor, trainer, facilitator, and coach in test automation and testing process improvement. Szilard is very involved in the testing community, and received the Tester of the Year in Finland award in 2024. He runs the Finnish Testing Meetup Group with his friends, is active in International Software Testing Qualifications Board (ISTQB) as Product Owner, and is a member of the Hungarian Software Testing Board (HTB). For many years, Szilard has been working on and supporting conferences like HUSTEF, UCAAT, EuroSTAR. In his personal life, he enjoys kayaking on the sea, playing with LEGO, and being tested by his teenage daughter :-)

part of the