
Daniel Ostrovsky
Daniel is an AI Architect at Payoneer with over two decades of experience leading development teams, both in Israel and abroad, from idea to production. His current focus is AI infrastructure and multi-agent systems in real-world use — the layer that ties together developer tools, knowledge graphs, and product delivery.
Daniel is a public speaker and a blog writer, and an active contributor to open source. He also runs the "NG-Heroes" meetup, a space for the local tech community to meet and share what they're learning. Outside of work, family comes first. He proudly holds the title of "The Best Developer in the World" — awarded by his wife, and he has no plans to give it back.
Interests:
react componentsweb developmenttoolingtypescriptreactgraphqllambdareact nativepatternsapi securitycssdesign systemsteam productivitydevtoolsnpmsoft skillsci cdfrontenddevopse2e testingawsbuilders and founderstestingbrowser apijavascriptbest practicescypressweb appsstate managementnode.jsweb componentsbuild toolsframeworksarchitectureapi developmentnext.jsperformanceunit testingscalabilityuser interfacesangularmicro-frontendsdatabaseadvanceddesigncode qualityreact hooksmicroservicesreact querywebpack
(MCP Security) - How Your Friendly MCP Tool Might Betray You
AI Coding Summit Berlin
Upcoming
(MCP Security) - How Your Friendly MCP Tool Might Betray You

We all love the convenience and power of AI-enhanced tools using MCP. But what if these handy servers had a hidden dark side? Let's dive into real-world examples of how MCP servers can silently leak your data, execute malicious commands, or even grant attackers access to your systems.
You’ll learn about sleeper attacks, tool poisoning, shadowing, and remote code execution—complete with chilling real-life cases and practical advice on defending yourself.
This is an eye-opening session that exposes why blind trust in MCP is a dangerous game.
You’ll learn about sleeper attacks, tool poisoning, shadowing, and remote code execution—complete with chilling real-life cases and practical advice on defending yourself.
This is an eye-opening session that exposes why blind trust in MCP is a dangerous game.
AI-Powered E2E UI Testing: Faster Creation, Easier Maintenance
JSNation US 2024
10 min
AI-Powered E2E UI Testing: Faster Creation, Easier Maintenance

This session will guide you through the advanced field of AI- E2E UI Testing, focusing on how it speeds up test creation and simplifies test maintenance. We'll begin by examining the challenges in generating E2E tests with AI, noting how this differs from the simpler task of creating unit tests.
The discussion will then shift to a solution that addresses these challenges effectively. Prepare to see a live demonstration where we'll craft an E2E test using popular tools like Cypress or Playwright. To wrap up, we'll look into how AI comes close to fully automating the maintenance of our test suites, ensuring they stay up-to-date with minimal manual intervention.
The discussion will then shift to a solution that addresses these challenges effectively. Prepare to see a live demonstration where we'll craft an E2E test using popular tools like Cypress or Playwright. To wrap up, we'll look into how AI comes close to fully automating the maintenance of our test suites, ensuring they stay up-to-date with minimal manual intervention.