AI Governance Engineer
GitHub

Red teaming

By Updated

Structured adversarial testing of a model or agent to elicit failures (jailbreaks, injection, tool misuse) before an attacker does; treated here as an evidence-producing control.

Developed in
ch. 05, Pattern: Adversarial Red-Team Suite
Chapters
ch. 04, The Stack · ch. 05, Patterns · ch. 15, Deployment
Source
Defined by this Body of Knowledge: the section it is developed in is the source

Where it is used

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

Red teaming: mentions per chapter33 mentions of the term across 16 of the 23 chapters of the Body of Knowledge; the chapters the glossary cross-references are drawn solid.Cross-referenced chapterOther chapter01 Definition: 1 mention01 Definition104 The Stack: 3 mentions04 The Stack305 Patterns: 5 mentions05 Patterns506 The Role: 4 mentions06 The Role407 Maturity Model: 1 mention07 Maturity Model108 Regulatory Map: 4 mentions08 Regulatory Map410 Reading List: 5 mentions10 Reading List512 Governance Program: 1 mention12 Governance Program113 Risk Management: 2 mentions13 Risk Management214 Development: 1 mention14 Development115 Deployment: 1 mention15 Deployment116 Fairness & XAI: 1 mention16 Fairness & XAI118 EU AI Act: 1 mention18 EU AI Act119 Privacy & AI: 1 mention19 Privacy & AI120 Existing Law: 1 mention20 Existing Law123 AI Agents: 1 mention23 AI Agents1No mentions in the other 7 chaptersSource: the Body of Knowledgev0.5.0
Red teaming: mentions per chapter33 mentions of the term across 16 of the 23 chapters of the Body of Knowledge; the chapters the glossary cross-references are drawn solid.Cross-referenced chapterOther chapter0001 Definition: 1 mention101020304 The Stack: 3 mentions30405 Patterns: 5 mentions50506 The Role: 4 mentions40607 Maturity Model: 1 mention10708 Regulatory Map: 4 mentions40810 Reading List: 5 mentions5101112 Governance Program: 1 mention11213 Risk Management: 2 mentions21314 Development: 1 mention11415 Deployment: 1 mention11516 Fairness & XAI: 1 mention1161718 EU AI Act: 1 mention11819 Privacy & AI: 1 mention11920 Existing Law: 1 mention120212223 AI Agents: 1 mention123Source: 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 Red teaming per chapter
ChapterMentionsCross-referenced
00 Preface0No
01 Definition1No
02 Why Now0No
03 Values & Principles0No
04 The Stack3Yes
05 Patterns5Yes
06 The Role4No
07 Maturity Model1No
08 Regulatory Map4No
10 Reading List5No
11 AI Defined0No
12 Governance Program1No
13 Risk Management2No
14 Development1No
15 Deployment1Yes
16 Fairness & XAI1No
17 Incidents0No
18 EU AI Act1No
19 Privacy & AI1No
20 Existing Law1No
21 AI Laws Worldwide0No
22 Principles & Standards0No
23 AI Agents1No

Patterns that use this term

5 pattern pages use the term, most mentions first.

Red teaming: 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 Evals05 AssuranceRed teamingRelated terms (1)Jailbreak · RelatedJailbreakPatterns using it (5)AI Threat Model, 1 mention · Uses the termAI Threat ModelAdversarial Red-Team Suite, 2 mentions · Uses the termAdversarial Red-Team SuiteClaims Substantiation Gate, 1 mention · Uses the termClaims Substantiation GateEval Gate in CI, 1 mention · Uses the termEval Gate in CIFairness Eval Suite, 1 mention · Uses the termFairness Eval Suite
Red teaming: 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 Evals05 AssuranceRelated terms (1)Jailbreak · RelatedJailbreakPatterns using it (5)AI Threat Model, 1 mention · Uses the termAI Threat ModelAdversarial Red-Team Suite, 2 mentions · Uses the termAdversarial Red-Team SuiteClaims Substantiation Gate, 1 mention · Uses the termClaims Substantiation GateEval Gate in CI, 1 mention · Uses the termEval Gate in CIFairness Eval Suite, 1 mention · Uses the termFairness Eval SuiteRed teaming
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 Red teaming
FamilyItemRelation
Related termsJailbreakRelated
Patterns using itAI Threat Model, 1 mentionUses the term
Patterns using itAdversarial Red-Team Suite, 2 mentionsUses the term
Patterns using itClaims Substantiation Gate, 1 mentionUses the term
Patterns using itEval Gate in CI, 1 mentionUses the term
Patterns using itFairness Eval Suite, 1 mentionUses the term
  • Jailbreak

    A prompt crafted to make a model disregard its safety instructions entirely.

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). Red teaming. In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0), Glossary. https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/glossary/red-teaming. CC BY 4.0

BibTeX

@misc{aige2026redteaming,
  author  = {Jorge García Aibar},
  title   = {{Red teaming}},
  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/red-teaming}
}