Agents

An AI agent is an LLM that can decide and take actions in a loop, using tools to pursue a goal rather than just replying once.

A chatbot replies, a workflow runs fixed steps, and an agent decides its own next step — knowing the difference tells you which to build.

The agent loop is the cycle of observe, reason, plan, and act that repeats — using tools and results — until the agent reaches its goal.

ReAct is an agent pattern that interleaves reasoning (Thought) with tool use (Action) and results (Observation), looping until it can answer.

Tool selection is how an agent picks the right tool for a step by matching the task to each tool's name and description — so good tool design is critical.

Agents use short-term memory (the context window), long-term memory (facts stored outside and retrieved), and state (task progress) to stay coherent over many steps.

Planning breaks a goal into sub-tasks before acting, and reflection lets the agent critique and fix its own work — together they make agents far more reliable.

Human-in-the-loop inserts a person's approval before risky or irreversible agent actions, combining autonomy with safety and accountability.

Multi-agent systems split a big task across specialized agents coordinated by an orchestrator, trading extra complexity and cost for better focus and parallelism.