KEYNOTE: Building Trust in AI Agents: Solving the Communication & Oracle Problems in Agentic Development
Agentic SW development is an active discussion point now, with the promise of improving efficiency ten fold. However, replacing the whole development process with agents is not a trivial task, especially if you are a Quality Assurance advocate always looking for risks.
I believe that designing the Development Value Stream with autonomous agents still has two major challenges:
- The communication problem
- The oracle problem
The interconnected system of AI Agents needs to be implemented with care to build a robust, effective and efficient process, giving an answer to both of these problems.
In my presentation, I would like to discuss how the challenges of communication and oracle are affecting the SW development process now, how they are handled with proper Quality Assurance practices in DevOps, and after the the key concepts of AI Agents present how to design the new AI Agentic Development process to provide high quality outcomes.
Szilárd Széll is a DevOps Transformation Lead, Test Coach, and SAFe 6.0 SPC at Eficode. He has years of experience with DevOps transformation, especially in the telco industry. 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. He runs the Finnish Testing Meetup Group, is active in International Software Testing Qualifications Board (ISTQB) working groups, 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, and Eficode's very own DEVOPS Conference.
In his personal life, he enjoys kayaking on the sea, playing with LEGO, and being tested by his teenage daughter :-)
