External taxonomies
SAICA-KG absorbs existing failure-mode taxonomies as first-class data and publishes explicit crosswalks from them into the KG's FailureMode facet.
9 Critical Failure Patterns of Coding Agents
v2026-01 · 9 categoriesColumbia DAPLab (Reya Vir and collaborators)
Empirical failure patterns observed across 15+ applications and 5 state-of-the-art coding agents (Claude Code, Cline, Cursor, v0, Replit).
Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes
v2026-03 · 30 categoriesShah et al. (arXiv:2603.06847)
Grounded-theory taxonomy of faults in agentic AI systems, derived from 13,602 issues and PRs across 40 open-source agentic-AI repositories, with stratified sampling to 385 faults and developer-study validation (n=145). Three parallel taxonomies: fault types (5 dimensions, 13 major categories, 37 fault subcategories); 13 symptom classes; 12 root-cause categories. This is the empirical corpus SAICA-KG uses for its v0.1 back-test.
MAST: Multi-Agent System Failure Taxonomy
v2025 · 14 categoriesCemri et al. (UC Berkeley + collaborators)
Failure modes of multi-agent LLM systems, grounded-theory derived from 1,600 annotated traces across 7 multi-agent frameworks.
Microsoft AI Red Team: Taxonomy of Failure Modes in Agentic AI Systems
v2025-04 · 18 categoriesMicrosoft AI Red Team (AIRT)
Failure modes of agentic AI systems, split along two axes: safety vs. security (impact) and novel vs. existing (whether the mode is unique to agentic AI or inherited from prior generative AI). Single- vs. multi-agent distinctions are surfaced in descriptions. Derived from Microsoft AI Red Team's operational experience and a 30-page April 2025 whitepaper.
OWASP Top 10 for Agentic Applications 2026
v2026 · 10 categoriesOWASP Gen AI Security Project
The ten most critical security risks facing autonomous and agentic AI applications. Globally peer-reviewed, developed with 100+ industry experts and researchers. The most visible formal taxonomy of agentic AI risk.
Swiss Cheese Model for AI Safety: Multi-Layered Runtime Guardrail Taxonomy
v2025-01 (v3) · 40 categoriesShamsujjoha, Lu, Zhao, Zhu (CSIRO Data61)
A SLR-derived taxonomy of multi-layered runtime guardrails for foundation-model-based agents. Organized along three architectural dimensions (pipelines, artifacts, actions) plus quality attributes that guardrails should satisfy. Evoked as a "Swiss Cheese" defense-in-depth reference architecture for AI safety by design.