NOW
Now
A monthly snapshot of what I’m building, learning, and exploring as a QA Engineer / SDET focused on AI testing.
Building
Products and tooling shipping right now.
- AI Test Case Generator
Shift testing left with multi-modal AI — PRD / image / video in, reviewable cases out.
- OpenClaw QA Skills
Installable ClawHub skills for QA and agent workflows.
- Test DB Docker Suite
Ready-to-run Dameng / Highgo / Kingbase / TiDB images for developers, QA, ops, and DBAs.
Learning
Skills and stacks I am actively leveling up.
- AI Agent Testing
How to test agents, tools, and multi-step workflows.
- MCP
Model Context Protocol for toolable agent systems.
- Playwright
Deeper fixtures, parallel runs, and CI patterns.
- LLM Evaluation
Eval harnesses, scoring, and regression for LLM outputs.
Exploring
Longer-horizon bets — research before commit.
- Autonomous Testing
Where agents can own exploration without losing signal.
- AI Test Agents
Specialized agents for case design, triage, and repair.
- Cloud-native Test Infrastructure
Ephemeral environments and portable QA stacks.