tangle-network/agent-app

eval-campaign

Wire product measurement and improvement to Agent Eval campaigns, official optimizers, and explicit release decisions.

Idioma do texto original: inglês

surface-evolution

Optimize one production agent surface with Agent Eval methods, separate data, bounded spend, and measured promotion.

Idioma do texto original: inglês

improve-conductor

The user-facing controller for the Improve button. Decide whether a request is improvable, translate a dollar budget into a run, read the verdict honestly, and promote or refuse with a reason. Never promise a lift you cannot measure.

Idioma do texto original: inglês

measurement-validation

Prove a measurement is sound BEFORE spending money optimizing against it. The gate that decides whether an Improve run is allowed to start, and whether its result is allowed to be believed. Refuse metrics whose noise exceeds the effect, that have no held-out…

Idioma do texto original: inglês

skill-evolution

How every skill in the Improve family stays agentic and general instead of rotting into a brittle rulebook. A skill is a measured hypothesis — a few human-owned invariants plus a wide loop-owned judgment surface that improves from outcome data via its own…

Idioma do texto original: inglês

eval-architect

Build a measurement that scores an agent's REAL deliverable — not a proxy — for a product you've never seen before. Use when scaffolding or repairing the eval an Improve loop optimizes against. Get this wrong and every downstream optimization perfects a…

Idioma do texto original: inglês

eval-bootstrap

When a product has NO improvement infrastructure yet, build it for real — elicit the RIGHT target, ground the measurement in external truth, and construct a validated harness (often via a delegated agent-runtime build loop) BEFORE any optimization spend. The…

Idioma do texto original: inglês