hi, I build software.
I'm Weng Jialin, a software engineer building AI Agent infrastructure and developer platforms. More about me →
Building a Lab for the Model
A performance-optimization case study showing how prompt contracts, multi-agent research, trace tooling, experimental memory, and validation turn an agent harness into a working environment for capable models.
Why Did .text Change When the Branch Name Changed?
A CI/CD infrastructure case study on why raw PE .text changes can be caused by relocation-covered address values rather than code logic changes, and why AI analysis still needs engineering validation.
Tokens Are Not Just a Cost Problem
Token management in AI agents is not a single compression trick. It is a system design problem around admission control, compression, retrieval, cache protection, output shaping, and overflow recovery.
The Next Layer of Agent Observability
Why agent observability needs to connect semantic traces, system-level facts, agent gateways, OpenTelemetry, evaluation, and policy into one governable trust chain.