An anti-pattern is a recurring solution that looks reasonable but reliably produces bad outcomes — and for which a better alternative is known. This guide names thirteen such anti-patterns from production AI-agent deployments and pairs each with a remediation grounded in OWASP LLM Top 10, NIST AI RMF, Microsoft SFI, and SLSA. A fourteenth article covers the ReAct engineering discipline that keeps these failure modes out in the first place. Start with Article 1 below, or use the Jump to article menu in the top navigation at any time.

Capability and credential boundaries

Untrusted content and influence

Supply chain and pipelines

Observability, governance, and trust calibration

About the series

Each article in this series names an anti-pattern that is well-attested across the industry but rarely discussed by its own name. Naming is not a stylistic choice. A pattern that has a name can be discussed in architecture review, raised in a procurement questionnaire, and recognised across teams. A pattern without a name has to be re-explained every time.

The references in each article point to the same small set of frameworks — OWASP, NIST, Microsoft Secure Future Initiative, SLSA, Zero Trust — chosen because they are the frameworks that procurement, audit, and regulators are most likely to ask about. Articles can be read individually; readers who work through the full set will notice that the controls compose, which is intentional.

More field guides