Platform Engineers Milano

Please, register for the event here

This webinar looks to develop strategies for mastering cost-effective AI agent evaluation at scale using stratified sampling, risk-based testing, and multi-stage screening to cut costs while maintaining enterprise-grade quality control.

This webinar will share key insights on AI agent evaluation and highlight how to:

• Cut evaluation costs through stratified sampling across personas and risk-based prioritisation, focusing resources on high-impact, high-variance scenarios rather than exhaustive testing.
• Build progressive evaluation systems using multi-stage screening that catches obvious issues cheaply, then applies deeper evaluation only where needed - balancing "vibes" for content vs rigorous testing for critical processes.
• Implement enterprise-ready observability with OpenTelemetry telemetry, persona coverage maps, and continuous calibration frameworks that adapt as your agentic platform scales and models evolve

After a 30-minute talk there’ll be a 15-minute Q&A, for which we encourage you to submit questions in advance.
A webinar recording and related materials will be shared with all attendees after the event.

Disclaimer: We use Zoom for the webinar stream. The link to the webinar will be sent upon your registration to your email.
____________
Speaker:
Glyn Darkin - Global Head of Delivery @ ClearRoute

Having worked in roles ranging from cold caller, marketer and lead engineer in several start-ups to Chief Architect in a Global SI, Glyn Darkin’s jack-of-all-trades aptitude and engineer’s mindset is a winning combination in his role as Global Head of Delivery. Quick to grasp the most convoluted business issue, he has an impressive track record of using technology to solve client problems. His past achievements include developing an award-winning digital mortgage product for a leading bank, and building TescoEntertainment

Fascinated by AI, Glyn’s current obsession is staying ahead of the sweeping changes it brings. At home, he spends his evenings coding to fully understand how the technology will affect not only ClearRoute’s ways of working, but the types of products and platforms we implement for our customers.

* Please register here

Discover why CI/CD pipelines weren’t built for today’s testing realities. As AI-driven development accelerates release cycles, traditional CI/CD pipelines are buckling under the weight of automated testing, leading to slower feedback, brittle environments, and rising infrastructure costs.

The truth is, CI/CD was designed for builds and deployments, not large-scale test execution. In this webinar, we’ll unpack why cloud-native leaders are moving beyond legacy pipelines and how purpose-built continuous testing platforms are helping teams achieve both speed and quality.

What attendees will learn during the webinar:

• Understand the architectural limits of CI/CD and how AI-driven development and rapid release cycles expose gaps in scalability, visibility, and reliability.
• Learn how leading engineering orgs unify test insights across tools, eliminate flaky environments with Kubernetes-native approaches, and cut infrastructure costs through smarter resource allocation.
• Discover how purpose-built continuous testing platforms, designed for speed, scale, and AI-enhanced delivery, are redefining how teams balance quality with velocity.

__________
Speaker:
Ole Lensmar - CTO @ Testkube

Ole started building with XML APIs in the late 90s and has since then worked with multiple technologies and startups, most notably as creator of SoapUI in 2004 and Chairman of the Swagger / OpenAPI Initiative in 2015. He joined Testkube at its inception in 2021 and is now entirely focused on ensuring its success at bringing continuous testing to the cloud-native space. When not at his laptop he can be found playing a guitar or riding a bike, but rarely both at the same time.

Please register here

Agentic AI for test data generation has arrived - but what does the ideal process look like and how will it fit within your workflows? Join synthetic data pioneer Mark Brocato as he spotlights the latest capabilities of Tonic Fabricate and speaks candidly on the potential and pitfalls of AI-driven data generation. With the right tools in place, the test data you need is just an AI conversation away.

• The pros and cons of various synthetic data strategies: Understand the trade-offs between rule-based synthesis, data de-identification, and Agentic AI to select the right fit for your workflows.
• How to generate highly realistic, nuanced data: Learn how Agentic AI creates complex test data for development and testing, significantly reducing the need for deep domain expertise.
• Actionable best practices and use cases: Determine the optimal AI approach for specific development needs, from prototyping to greenfield development, and performance to load testing.

____________
Speaker:
Mark Brocato - Head of Engineering for Fabricate @ Tonic.ai

Mark Brocato is a software developer and entrepreneur best known as the founder of Mockaroo, one of the world’s leading synthetic data generators, launched in 2014. The idea for Mockaroo came while Mark was watching QA engineers struggle to test complex life science workflows at a startup called BioFortis, inspiring him to make realistic test data easier for everyone. With over two decades in software development, he’s built tools for developers at Sencha, Layer0, and beyond. In 2024, Mark launched Fabricate, the AI-powered synthetic data platform that was acquired by Tonic.ai in 2025, where Mark continues to lead its development. A Ruby, JavaScript, and Rust developer, he divides his time between Sparta, New Jersey, and Tallinn, Estonia.