Writing
Verified, Not Trusted: Expense Analysis, Part Two
Imperative Python controls expense analysis and verifies model contributions through source evidence, reconciliation, and exact calculations. Models handle bounded judgments.
Topic
Confidence-Gated Routing
Using a model’s answer and tested confidence thresholds to choose between automatic action, another process, and human review.
2 pages
Writing
Jev: A Practical Reference
Jev makes bounded semantic judgments with Choice, Score, and Noul; code handles exact work and policy, while evaluation and confidence gates determine when to act or escalate.