AI agent
What is AI agent?
An AI agent is a system built on a large language model that can plan multi-step actions, call external tools or APIs, and use their results to decide what to do next, rather than only returning a single one-shot text response. In a CPaaS context, an AI voice or chat agent can look up an order, place an outbound notification, or escalate to a human — chaining tool calls together to complete a task, not just answer a question.
More detail
What separates an agent from a simple chatbot is the tool-calling loop: the model decides which action to take, observes the result, and decides the next action, repeating until the task is done or it hands off to a human.
Production AI agents typically run behind guardrails and evals that constrain which tools they can call and validate their behavior before and after each release, since an unconstrained agent can take unintended actions.
Frequently asked
- What's the difference between an AI agent and a chatbot?
- A chatbot typically returns a single text response per turn; an AI agent can plan multiple steps, call external tools or APIs, observe the results, and decide what to do next — chaining actions together to complete a task rather than just answering a question.
- How does an AI agent know which tool to call?
- The underlying language model is given a list of available tools with descriptions of what each does, and it selects and calls the appropriate one based on the current step in the task — a pattern called tool calling.
See also
Build it on Orbit
Voice, messaging, email, video, and AI agents on one platform and one pay-as-you-go bill. Start free — no credit card required.