tangle-network
@tangle-network Organization
Public Skills
eval-architect
by tangle-network
Build or repair evaluations that score the agent's actual deliverable through the production path, with independent controls and visible missing evidence.
measurement-validation
by tangle-network
Check whether an evaluation supports an optimization or release decision through calibrated scoring, independent comparison units, and complete paired evidence.
improve-conductor
by tangle-network
Drive a requested optimization from its target and resource limits through measured candidate selection, evidence review, and the product's promotion policy.
surface-evolution
by tangle-network
Optimize one production agent surface with Agent Eval methods, separate data, bounded spend, and measured promotion.
eval-campaign
by tangle-network
Wire product measurement and improvement to Agent Eval campaigns, official optimizers, and explicit release decisions.
skill-evolution
by tangle-network
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 meta-eval. This is the recursion that lets the agent builder learn to build improvable agents.
eval-bootstrap
by tangle-network
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 anti-toy, anti-circular skill: it exists so the improver moves what the user actually wants, not a measurable proxy it invented.