Models

A model is a named, trained artifact that scores content along one or more traits. Each model encodes a specific standard for a specific kind of content; scoring the same text against different models produces different results, because the models measure different things.

§1Definition

A model consists of a handle, a description, and a set of traits with trained parameters. The handle identifies the model for the API and MCP; the description summarizes what the model measures; the traits define the axes on which content is scored. A model is self-contained: once trained, scoring against it requires only the model and the content.

u22a8.technical-writing 3 traits
Scores technical prose for clarity and specificity.
clarity
◂ ObscureClear ▸
specificity
◂ GeneralSpecific ▸
verification
◂ AssertedEarned ▸
Figure 1. A model — handle, description, and three traits, each with polarity labels at the ends of the scale.

§2Mechanism

§2.1What scoring against a model produces

When content is scored against a model, each declared trait produces a score on the 0–100 axis along with its tier label, confidence level, and headroom. A composite — the harmonic mean of the per-trait scores — is returned alongside the per-trait results. The format of the combined output is described on the score card page.

§2.2Models are trained, not configured

A model's trait axes and break values are fit during training from the supervision supplied at that time. The trained parameters are stored on the model and used at scoring time. A model is not a set of rules or weights the user adjusts; changes to scoring behavior come from retraining with updated supervision, not from reconfiguring a deployed model.

§3Different models, different standards

Models are narrow. A model trained to score technical writing measures a different set of traits than a model trained to score landing pages, and both differ from a model trained on policy documents. A given piece of content scored against two models receives two unrelated results, because the two models are answering two different questions.

u22a8.technical-writing
clarity
specificity
verification
u22a8.compelling-readme
hook
structure
proof
call to action
Figure 2. Two models with different trait sets. Neither model's scores are directly comparable to the other's; each model evaluates its own domain.

§4Portability

A model is addressed by its handle across every scoring surface — the REST API, the MCP server, the GitHub Action, and the web UI. The same model produces the same output for the same content regardless of which surface issued the scoring call; scoring is deterministic given a fixed model and fixed content.

§5Related concepts

  • Traits — the scoring axes a model declares.
  • Score card — the output returned when content is scored against a model.
  • Training — the process that produces a model from supervision.
Scores are approximate — not a substitute for human judgment.