Abdelrahman Khalil Abbas

I'm a certified Software Test Engineer focused on making sure mobile and web applications hold up under real-world use — not just the happy path. That means designing test cases that account for interruptions, edge cases, and the messy ways people actually use apps.

Most of my work sits at the intersection of manual judgment and automation: knowing when a script can do the job, and when a human — or increasingly, an AI agent — needs to look closer.

Lately, I've been exploring agentic AI approaches to testing: building tools that can read a user story, navigate an app on their own, and judge whether the result is actually correct, not just whether a script executed.

That work has pulled me into AI and prompt engineering more broadly — designing the prompts and logic that let an AI agent make good judgment calls, and contributing to internal engineering tools that use AI to help teams plan and track their work.