What Agents Are

If you cannot define what your agent is, you cannot make it reliable. An agent is not a chatbot. It is a system that observes a context, decides on a next action, executes that action through tools, and updates state until a goal is met or a budget is exhausted.

A workflow is a fixed path. An agent is a controlled loop. The distinction matters because agents must survive ambiguity, retries, and partial progress. This lesson is about naming that loop and setting the boundaries that keep it safe.

The Agent Loop

At minimum, an agent needs five things:

1. Goal: a clear success condition.
2. Context: inputs, constraints, and the current world state.
3. Policy: the decision rule that chooses the next action.
4. Tools: the allowed actions and their schemas.
5. State: what the agent has done and learned so far.

When these are explicit, you can debug and test them. When they are implicit, you get chaos.

// Minimal agent loop, intentionally small
export type AgentState = {
  goal: string;
  context: string;
  history: Array<{ role: "system" | "user" | "assistant"; content: string }>;
  stepsTaken: number;
  maxSteps: number;
};

export async function runAgent(state: AgentState) {
  while (state.stepsTaken < state.maxSteps) {
    const plan = await decideNextAction(state); // model policy
    const result = await executeTool(plan.tool, plan.input); // tool call
    state = updateState(state, plan, result); // state transition

    if (isGoalMet(state, result)) break;
  }

  return state;
}

This loop is small on purpose. Every production agent is a variation of this.

Boundary 1: The Goal Contract

Your agent must know what success looks like. Define it as a check that can be evaluated without calling the model again. For example: "Return a JSON object with a validated email and a completed onboarding checklist." The goal is not "help the user" or "be useful." Vague goals are untestable.

Boundary 2: The Action Surface

Agents are powerful because they can act, but that is also where they break. Every tool must have:

• A single responsibility
• A strict schema
• A timeout and error code
• A clear side effect description

If a tool is fuzzy, the model will misuse it. If a tool is broad, a single mistake can cause damage.

Boundary 3: The Budget

An agent without a budget will loop forever. Budgets are not just costs. They are also step limits, API rate limits, and timeouts. You should define all three and enforce them at runtime.