01
Agent Reliability Lab
An experimental platform for verification, recovery, and observability in multi-step AI agents.
Software Engineer · Class of 2026
Open to full-time software and AI engineering rolesTurning complex problems
into reliable software.
I explore AI agents, developer tools, and reliable software systems—turning ambiguous problems into outcomes that can be verified.
Work samples
Selected projects
↗
02
Bilingual Knowledge Garden
A searchable bilingual knowledge base connecting reading notes, code experiments, and long-running themes.
03
Local-first Dev Environment
A reproducible and reversible Linux workstation and developer-tool configuration.
Field notes
Recent posts
01
From Running to Reliable
Why exit code zero does not mean the job is done, and how to define meaningful acceptance rules for automation.
02
Modeling Bilingual Content for a Personal Site
A language switcher is not enough; routes, content identity, and missing translations all need explicit rules.
03
A Project Page Is Not a Stack Showcase
Problems, constraints, tradeoffs, and evidence reveal more than a wall of framework badges.
Have a problem worth solving well?
hello@szchan.net↗