Get started

Recording a provider term

Source

Entering, by hand, what a provider published about how it handles the work: retention, training use, processing regions, whether a key you hold is accepted. Each reading is taken from a page on the provider's own domain.

bash
npm run term:add -- --provider openai --kind zero_retention --value yes --on 2026-08-27 --source-url https://openai.com/enterprise-privacy
FlagMeaning
--providerThe provider it is about
--kindOne of zero_retention, no_training, regions, byok
--valueyes or no, or comma-separated region codes for regions
--onThe date somebody read the page. Never a date in the future
--source-urlThe page it was read from, on that provider's own domain
--noteWhat the page scoped it to, if it scoped it

The four refusals it inherits

They are the curated log's, applied through the same function:

  1. No source URL, no row.
  2. http is not a source.
  3. A host that is not the provider's is not the provider.
  4. A URL that does not answer 200 today is not verified today.

Plus two of its own. A value that is not one the kind accepts is refused rather than stored, because "the term answers whether the provider trains on customer data, and a hedge is not an answer this record can hold". And a second reading of the same kind on the same day is refused, because a term that changed is a new row on the day it was read, never an edit of the one a decision was taken under.

Why a person and not an adapter

A policy page is prose and the answer is a yes or a no. A parser deciding what "we do not retain your data" means would be interpolating exactly where the honesty contract forbids it.

What it is for

A workload requires one, and a candidate whose provider does not meet it is excluded before anything is weighed:

bash
npm run aperture:workload:edit -- acme/support --constraint requiresZeroRetention=true

Provider term is exact about what a requirement means when the record holds no term to check it against, which is the case worth reading before you rely on one.