How evals went from research curiosity to the only thing that ships — a five-year history — step 7 of 8

Write eval_readiness(team) that takes a team profile (dict) and returns a dict with two fields:

• score: integer 0-100, higher means MORE eval discipline (good)
• verdict: string, one of:
  • "eval-mature" if score >= 80
  • "eval-aware" if score >= 50
  • "eval-curious" if score >= 20
  • "vibes era" if score < 20

Score the team on these signals (each adds points to the readiness total):

• has_test_set is True: add 25 (ground-truth cases exist)
• has_judge_prompt is True: add 15 (rubric or LLM-as-judge defined somewhere)
• ci_runs_evals is True: add 25 (the regression gate)
• tracks_eval_history is True: add 15 (can compare runs over time)
• eval_count_per_feature >= 20: add 20 (enough cases to catch obvious regressions)

Two teams run. Expected output:

EvalMatureCo: {'score': 100, 'verdict': 'eval-mature'}
VibeCo:       {'score': 0, 'verdict': 'vibes era'}