AI is now part of how software gets built, what organisations put in front of their customers, and how they plan to create value. Yet, the hardest question remains the simplest one: does it actually work, and how do we know? Over breakfast, Itecor looks at that question from three angles.
First, AI in the Process: where AI delivers real efficiency gains across the software lifecycle (SDLC), and where it’s still hype, with a live example from requirement to automated test. Second, AI in the Product: how to test a customer-facing AI assistant where incorrect answers can have serious consequences. Third, AI and Value Creation: why moving from experiments to measurable outcomes is itself a testing journey, and what that means for governance, skills and the way we all work.
itecor testing breakfast
Thursday, November 12th 2026
08:00-10:00h
Hotel Warwick, Geneva
Where AI Really Pays Off in the Software Lifecycle
Speaker: Alexandre Thibaud
AI can now touch every stage of software delivery, but the gains aren’t spread evenly. In this session, we walk through the lifecycle from requirements to release, show where AI makes a measurable difference today and where it’s still hype, and share the practices we’ve found work.
We’ll finish with a live example: taking a requirement through AI-assisted review, test design, and automation inside Azure DevOps.
Good Enough to Ship? Testing Customer-Facing AI
Speaker: Yuval Keren
Pass/fail testing breaks the moment the same question gets two different answers.
In this session, Itecor shares the method we used to test a multilingual, customer-facing AI assistant: measuring failure rates across repeated runs instead of single verdicts, replacing «expected answers» with mandatory facts and source evidence, using an independent LLM as judge (calibrated against human experts first), and pinpointing whether a wrong answer came from the search step or the writing step.
You’ll leave with seven test campaigns, the order to run them in, and the open-source tools behind each one.
From AI Hype to Enterprise Value: We All Become Testers
Speaker: Amine Mansour
AI is democratising innovation: everyone can now generate ideas, prototype solutions and have an opinion on what “good” looks like. The challenge for enterprises is no longer finding AI use cases, but identifying which ones truly create value and can safely scale.
Drawing from real Data & AI transformation experience, this session will look at value realization as a continuous testing journey: from the business hypothesis and underlying data to the AI solution, adoption and measurable outcomes. We will explore what happens when requirements, data and expectations constantly evolve, why we all increasingly become “testers”, and how governance, critical thinking and upskilling can help organisations channel this democratisation without slowing it down.
Private event – registration required
This event is reserved for our clients and business contacts. As places are limited, registration is required.
Interested? Contact your Itecor Account Manager or email us at info@itecor.com.
más insights
Tricentis Transform London 2026: Agentic AI is redefining the boundaries of Quality Engineering
company newsquality assurance & testing
octubre 30, 2026
AI enhances the consultant, the consultant gives meaning to AI
company newsdigital solutionsgovernance & service managementquality assurance & testing
junio 09, 2026
AIOps and observability: when AI automatically detects problems in production
quality assurance & testing
mayo 18, 2026
