AI Governance Engineer
GitHub

Evals

By Updated

Automated tests of a model's or agent's behaviour (capability, safety and adversarial), run as controls, not as one-off research.

Developed in
ch. 04, Layer 03: Evals & Red Teaming as Evidence
Chapters
ch. 04, The Stack
Source
Defined by this Body of Knowledge: the section it is developed in is the source

Where it is used

20 chapters of the Body of Knowledge use the term. Each link opens the first section that does.

Evals: mentions per chapter131 mentions of the term across 20 of the 23 chapters of the Body of Knowledge; the chapters the glossary cross-references are drawn solid.Cross-referenced chapterOther chapter01 Definition: 7 mentions01 Definition703 Values & Principles: 4 mentions03 Values & Principles404 The Stack: 15 mentions04 The Stack1505 Patterns: 7 mentions05 Patterns706 The Role: 6 mentions06 The Role607 Maturity Model: 10 mentions07 Maturity Model1008 Regulatory Map: 11 mentions08 Regulatory Map1110 Reading List: 5 mentions10 Reading List511 AI Defined: 16 mentions11 AI Defined1612 Governance Program: 4 mentions12 Governance Program413 Risk Management: 11 mentions13 Risk Management1114 Development: 3 mentions14 Development315 Deployment: 9 mentions15 Deployment916 Fairness & XAI: 4 mentions16 Fairness & XAI417 Incidents: 1 mention17 Incidents118 EU AI Act: 1 mention18 EU AI Act119 Privacy & AI: 2 mentions19 Privacy & AI220 Existing Law: 2 mentions20 Existing Law222 Principles & Standards: 8 mentions22 Principles & Standards823 AI Agents: 5 mentions23 AI Agents5No mentions in the other 3 chaptersSource: the Body of Knowledgev0.5.0
Evals: mentions per chapter131 mentions of the term across 20 of the 23 chapters of the Body of Knowledge; the chapters the glossary cross-references are drawn solid.Cross-referenced chapterOther chapter0001 Definition: 7 mentions7010203 Values & Principles: 4 mentions40304 The Stack: 15 mentions150405 Patterns: 7 mentions70506 The Role: 6 mentions60607 Maturity Model: 10 mentions100708 Regulatory Map: 11 mentions110810 Reading List: 5 mentions51011 AI Defined: 16 mentions161112 Governance Program: 4 mentions41213 Risk Management: 11 mentions111314 Development: 3 mentions31415 Deployment: 9 mentions91516 Fairness & XAI: 4 mentions41617 Incidents: 1 mention11718 EU AI Act: 1 mention11819 Privacy & AI: 2 mentions21920 Existing Law: 2 mentions2202122 Principles & Standards: 8 mentions82223 AI Agents: 5 mentions523Source: the Body of Knowledge v0.5.0
Mentions per chapter How often each chapter names the term, with the chapters the glossary cross-references drawn solid. The longest bar is where to read the term in use; bars spread across many chapters mark a term that runs through the discipline.
Mentions as a table
Mentions of Evals per chapter
ChapterMentionsCross-referenced
00 Preface0No
01 Definition7No
02 Why Now0No
03 Values & Principles4No
04 The Stack15Yes
05 Patterns7No
06 The Role6No
07 Maturity Model10No
08 Regulatory Map11No
10 Reading List5No
11 AI Defined16No
12 Governance Program4No
13 Risk Management11No
14 Development3No
15 Deployment9No
16 Fairness & XAI4No
17 Incidents1No
18 EU AI Act1No
19 Privacy & AI2No
20 Existing Law2No
21 AI Laws Worldwide0No
22 Principles & Standards8No
23 AI Agents5No

Patterns that use this term

10 pattern pages use the term, most mentions first.

Evals: related terms and patternsThe term at the centre; related terms on solid edges, the terms it is contrasted with on dashed edges, and the patterns that use it most in the colour of their layer.RelatedColour: stack layer of the pattern01 Govern-as-Code03 Evals04 Runtime Controls05 AssuranceEvalsRelated terms (8)Generative AI · RelatedGenerative AIMachine unlearning · RelatedMachine unlearningModel anonymity · RelatedModel anonymityMultimodal model · RelatedMultimodal modelOpen-weight model · RelatedOpen-weight modelPrompt injection · RelatedPrompt injectionRegurgitation · RelatedRegurgitationReinforcement learning · RelatedReinforcement learningPatterns using it most (6)Adversarial Red-Team Suite, 1 mention · Uses the termAdversarial Red-Team SuiteClaims Substantiation Gate, 4 mentions · Uses the termClaims Substantiation GateDrift & Fairness Monitor, 2 mentions · Uses the termDrift & Fairness MonitorEval Gate in CI, 1 mention · Uses the termEval Gate in CIRuntime Guardrail, 2 mentions · Uses the termRuntime GuardrailUse-Case Intake & Risk Tiering, 2 mentions · Uses the termUse-Case Intake & Risk Tiering
Evals: related terms and patternsThe term at the centre; related terms on solid edges, the terms it is contrasted with on dashed edges, and the patterns that use it most in the colour of their layer.RelatedColour: stack layer of the pattern01 Govern-as-Code03 Evals04 Runtime Controls05 AssuranceRelated terms (8)Generative AI · RelatedGenerative AIMachine unlearning · RelatedMachine unlearningModel anonymity · RelatedModel anonymityMultimodal model · RelatedMultimodal modelOpen-weight model · RelatedOpen-weight modelPrompt injection · RelatedPrompt injectionRegurgitation · RelatedRegurgitationReinforcement learning · RelatedReinforcement learningPatterns using it most (6)Adversarial Red-Team Suite, 1 mention · Uses the termAdversarial Red-Team SuiteClaims Substantiation Gate, 4 mentions · Uses the termClaims Substantiation GateDrift & Fairness Monitor, 2 mentions · Uses the termDrift & Fairness MonitorEval Gate in CI, 1 mention · Uses the termEval Gate in CIRuntime Guardrail, 2 mentions · Uses the termRuntime GuardrailUse-Case Intake & Risk Tiering, 2 mentions · Uses the termUse-Case Intake & Risk TieringEvals
The term's neighbourhood Terms related to this one on solid edges, terms it is often confused with on dashed edges, and the patterns that use it most in the colour of their layer. Follow a dashed edge to check the distinction before you use either term.
Neighbourhood as a table
Neighbourhood of Evals
FamilyItemRelation
Related termsGenerative AIRelated
Related termsMachine unlearningRelated
Related termsModel anonymityRelated
Related termsMultimodal modelRelated
Related termsOpen-weight modelRelated
Related termsPrompt injectionRelated
Related termsRegurgitationRelated
Related termsReinforcement learningRelated
Patterns using it mostAdversarial Red-Team Suite, 1 mentionUses the term
Patterns using it mostClaims Substantiation Gate, 4 mentionsUses the term
Patterns using it mostDrift & Fairness Monitor, 2 mentionsUses the term
Patterns using it mostEval Gate in CI, 1 mentionUses the term
Patterns using it mostRuntime Guardrail, 2 mentionsUses the term
Patterns using it mostUse-Case Intake & Risk Tiering, 2 mentionsUses the term
  • Reinforcement learning

    Learning to maximise a reward signal through trial and feedback.

  • Machine unlearning

    Techniques that remove a training record's influence from a model without full retraining.

  • Open-weight model

    A model whose trained weights are published for download under a licence that may be permissive, copyleft, use-restricted or custom.

  • Multimodal model

    A model that takes or produces more than one modality (text, image, audio, video).

  • Prompt injection

    An input that alters a model's behaviour or output in ways its designers did not intend.

  • Model anonymity

    The EDPB's test for when a trained model falls outside the GDPR: both direct extraction of training subjects' data and obtaining it through queries must be…

  • Generative AI

    AI that outputs new content (text, images, audio, video, code) rather than an estimate about something that exists.

  • Regurgitation

    A model reproducing memorised training data verbatim, including personal data, whether prompted deliberately (training-data extraction) or not.

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. 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. CC BY 4.0

BibTeX

@misc{aige2026evals,
  author  = {Jorge García Aibar},
  title   = {{Evals}},
  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}
}