Skip to content
Awsaf Alam
Work
Research
Blog
About
Resume
GitHub
LinkedIn
Evals
View all tags
Record and replay: deterministic evals for LLM agents
10.03.2026
—
AI Agents
,
Testing
,
Evals
When to replace regex checks with an LLM judge (and how to test the judge)
14.10.2025
—
AI
,
Evals