Skip to main content

Anti-Patterns

These are the mistakes teams make repeatedly when building LLM-powered agents. Each is well-documented, widely recognized by practitioners, and observed in production systems. They're ordered roughly by how often they appear.

Learning these is faster than discovering them yourself.


Anti-Patterns

Anti-PatternThe Mistake
Framework TrapReaching for agent frameworks before understanding the problem
Prompt MonolithStuffing all instructions into a single massive prompt
Infinite LoopDeploying agents without hard limits on iterations, cost, or time
Vibe-Based DeploymentShipping changes based on gut feel instead of evaluation
Agent SprawlUsing multi-agent when a single agent would suffice
Tool Junk DrawerExposing too many poorly designed tools
Happy Path MirageTesting only clean inputs, ignoring adversarial and edge cases
Amnesiac AgentFailing to manage what the agent remembers across turns and sessions