Commit Graph

2 Commits

Author SHA1 Message Date
admin d2efc7030a feat: US-019 - Run benchmark and validate accuracy
Benchmark passes 19/20 (threshold 18/20) with no zeros.
Structural improvements: Employment Timeline section, leadership
labels on Tesco bullets, GPhC clarification, prompt trimming.
Fixed Q10 expected answer to match actual CV data.
2026-02-16 00:59:37 +00:00
admin 8cc7038942 feat: US-015 - Migrate benchmark script to OpenRouter 2026-02-16 00:31:16 +00:00