Foundations
Tool calling, planning vs reactive, and the limits youβll hit in prod.
Build Your First AI Agent
β ββWe write the simplest agent that actually works - no magic, no frameworks.
Learn the patternImplementationsHow AI Agents Use Tools (Basics)
β ββTool calling basics for AI agents: action schema, validation, execution boundary, and stop reasons for reliable production behavior.
Learn the patternImplementationsHow AI Agents Are Allowed to Use Tools
β β βTool calls are where agents break production: schema drift, retries, side effects, and that same 'oops' admin token. Here's how to survive.
Learn the patternImplementationsPlanning vs Reactive: How AI Agents Choose the Next Step
β ββPlanning vs reactive agent loops: trade-offs, failure modes, and when to choose each strategy for reliable tool-based execution.
Learn the patternImplementationsWhy AI Agents Fail
β β βUnderstand why LLM agents fail: hallucinations, context limits, tool errors, and the engineering guardrails that make agent behavior reliable.
Learn the patternImplementationsHow AI Agents Use Memory
β ββWithout this, every new action would be like a first attempt. Sometimes endlessly.
Learn the patternImplementationsWhat AI Agents Are Allowed to Do
β ββHow to define allowed actions for AI agents with least-privilege policies, explicit denies, and safe defaults for production systems.
Learn the patternImplementationsWhen AI Agents Should Stop
β ββBecause its job is to complete work. Not decide when enough is enough.
Learn the patternImplementations