AI evaluation design
Turn a product requirement into a graded test set with metric floors that block a release.
- SFIA 9
TEST Functional testing ↗ · level 4, Enable
Evidence: Designed a 260-question adjudicated golden set with six release floors that block changes (SEBI Circular RAG).MLNG Machine learning ↗ · level 4, Enable
Evidence: Selects models on measured benefit with baselines and significance tests (CodeSearchNet; SEBI ADR-004).- ESCO
- apply statistical analysis techniques ↗ · report test findings ↗
- O*NET
- Evaluating Information to Determine Compliance with Standards · Analyzing Data or Information
- NACE
- Critical Thinking
- Evidence
- 8 public links