AI Governance Engineer
GitHub

Evals as evidence

By Updated

The principle that the eval run is the assurance evidence: a failing eval blocks the build and its structured result is stored as proof the control fired.

Developed in
ch. 03, 2. Evals fail builds; reviews only recommend
Chapters
ch. 03, Values & Principles · ch. 04, The Stack
In the open reference
Evaluation environment control profile
Source
Defined by this Body of Knowledge: the section it is developed in is the source

Where it is used

One chapter of the Body of Knowledge uses the term. Each link opens the first section that does.

Sources

No external source: the term is coined or used in a specific sense by this Body of Knowledge, and the section linked under "Developed in" is its source.

Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .

Cite this term

García Aibar, J. (2026). Evals as evidence. In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0), Glossary. https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/glossary/evals-as-evidence. CC BY 4.0

BibTeX

@misc{aige2026evalsasevidence,
  author  = {Jorge García Aibar},
  title   = {{Evals as evidence}},
  note    = {Glossary, AI Governance Engineering: The Thesis \& Body of Knowledge, version 0.5.0},
  year    = {2026},
  doi     = {10.5281/zenodo.22956197},
  url     = {https://aigovernanceengineer.com/glossary/evals-as-evidence}
}