An AI agent is software that uses a language model to decide which steps to take, and which tools to use, in order to finish a task. You give it a goal, such as "answer this customer email". It works out what it needs to know, looks those things up, and produces a result. A text generator answers from what it was handed. An agent goes and gets what it needs.
We run AI agents on live customer service for an online brand. The example below is what one of them does with a single email. The volumes are in our case study.
A working example
A customer writes that their parcel is marked delivered and nothing has arrived. The agent:
- reads the email, plus a summary of the earlier messages in the same thread;
- finds the order from the sender's address and the order number in the text;
- asks the carrier's tracking service for the current status;
- searches the knowledge base for how the company handles this situation;
- looks up past mistakes recorded for this kind of case;
- writes the reply in the customer's language;
- decides whether this is a reply it may send alone or one a person must approve.
Nobody listed those steps for it in that order. A different email, such as a question about battery range, leads to different steps: no order lookup, one knowledge base search, an answer.
The parts of an AI agent
- A language model. It reads the input and decides the next step.
- Tools. Functions the model can call: look up an order, read tracking, search the knowledge base, create a ticket. Without tools, a model can only talk.
- Instructions. What the job is and what a good result looks like.
- Context. The facts of this case, prepared for the model: what the customer wants, what has been promised, what has been done.
- Limits. What the agent may do alone and what needs a person.
AI agent, chatbot, workflow
A chatbot is a conversation window. What sits behind it can be a script, a model, or an agent. A workflow is a set of steps drawn in advance: every case follows the same path. An agent chooses its path case by case. The three are compared in AI agent vs chatbot and AI agent vs workflow.
Types of AI agents
Textbooks sort agents by how they decide: simple reflex agents, model-based agents, goal-based agents, utility-based agents and learning agents. That list describes the inside.
For a business, the useful split is by what the agent is allowed to do:
- Answers. It reads and replies. Nothing changes in any system.
- Prepares. It gathers the facts, proposes a solution and drafts the reply. A person approves.
- Acts within limits. It sends simple replies and creates tickets on its own, inside rules a person set.
All three run side by side in the deployment we operate. In the 30 days to 19 November 2026, the chat agent handled 15,725 conversations with no message typed by a human agent. In email, 26,451 replies went out using an AI draft: the AI sent 3,331 on its own, agents sent 3,781 without changing a word, and agents edited 19,339 before sending.
What an AI agent is not
- It is not a colleague with a memory. It knows about yesterday only if the system hands it the facts.
- It is not always right. A model can state things that are false. The cases we caught are in hallucination examples and fixes.
- It is not the answer to every job. If the steps can be drawn in advance, a workflow is cheaper and behaves the same way every time.
What makes an agent work on real cases
Facts, not raw material. A model handed a whole email thread or a whole order misses the point. On one email about spare parts, we passed only the order lines the email concerned. The input fell from 37,604 tokens to 4,722, and all four parts in the reply were then correct.
One source for the rules. How to speak to a customer is written once, and every part of the system refers to that one text.
A person where money moves. Refunds, compensation and replacements are approved by a person. The agent prepares them.
Measurement by what people change. Every edit an agent's reviewer makes is a signal about what the agent got wrong.
Do you need one?
An AI agent fits a job that repeats every day, in real volume, with a system behind it to look things up in, and where the steps differ from case to case. Customer service email is the plainest example. Nine more are in AI agent use cases.
Tell us the job in one line and the free plan describes, within two working days, what an agent would handle and what stays with your people.
Originally published at ai.dingboai.com. Dingbo AI builds and runs AI agents for customer service, paid per completed task.
Top comments (0)