AI Agent Use Cases: 9 Jobs Running in Production
Lists of AI agent use cases tend to describe what an agent could do. This one lists nine jobs that AI agents do every day in systems we built and run, with the volumes where we have counted them. Most of the numbers come from one deployment, an e-bike brand selling through nine online storefronts in eight languages, described in our case study.
What makes a job a good use case
Four conditions, and a job needs all of them:
- It happens every day, in volume.
- It follows rules that can be written down.
- The facts it needs live in a system the agent can read.
- Its results can be counted and checked.
Each job below meets all four.
1. Answering customer chat
The agent answers questions about products, stock, shipping, usage, troubleshooting and published policy, in the customer's language. Volume in the last 30 days: 15,445 conversations with 36,309 customer messages. Agents stepped into the chat window zero times.
2. Looking up orders and shipments
The agent finds the order by number or checkout email, confirms the match, reads the carrier's tracking status and explains it in plain words. It reads and never writes: no order edits, no cancellations. Details are in AI chatbot order tracking.
3. Drafting a reply to every customer email
For each incoming email the agent distils the thread into structured facts, checks the order, the shipment and the knowledge base, proposes a solution and writes the reply. Volume: 36,294 customer emails in 30 days, and 204,910 drafts since June. Agents approved 3,463 of the last 30 days' replies without an edit and edited 19,357 before sending.
4. Sending simple replies on its own
Replies that involve no money, no promise and no policy exception go out without waiting for a person: tracking answers, links to manuals, a thank-you that closes a finished conversation. Volume: 2,756 emails in 30 days. The agent stops doing this on a ticket once a person is following it.
5. Sorting the inbox
Across several support mailboxes the agent sorts incoming mail by what must happen next, closes automated messages, merges emails from the same customer into one ticket and chases overdue cases. The method is in AI ticket triage.
6. Turning chat requests into tickets
When a chat customer needs an action, such as a refund, a return, a cancellation, an address change or an invoice, the agent does not agree to it. It creates a ticket carrying the facts already established, gives the customer the ticket number and the follow-up email address, and the email team takes it from there.
7. Preparing decisions for approval
For refunds, reshipments, replacements and returns, the agent prepares the plan: what happened, what the policy says, what it proposes, and the reply that would go out. A person approves, edits or changes the decision. An agent can answer "make it €30" and the plan is redone.
8. Recording what was approved
Once a person approves a solution, the agent writes it into the execution ledger with an owner and posts a short card to the team's group chat, so the people who carry it out see the task without anyone retyping it. Solutions the AI handled on its own wait in a review queue and are executed after a reviewer approves them. The ledger records the version a person finally approved, never the AI's first draft.
9. Reports and documents
Two jobs outside the inbox run the same way. A weekly voice-of-customer report reads the chat and email history and pulls out the week's pain points, selling points and unanswered questions. A bulk document job takes a spreadsheet and a template and produces one contract, notice or certificate per row as Word or PDF, sends each one and marks it as sent.
What the nine have in common
In every job the agent does the reading, checking and writing, and a person keeps any decision that costs money or moves goods. Every result is written back to a record, and a failed action is reported. That is why each job can be counted, and why we charge for these jobs by completed work.
Converted to working time, the chat and email jobs alone equal 3,900 hours of work in 30 days, at 3 minutes per chat message and 5 minutes per reply sent. The method behind that figure is in how to calculate AI agent ROI.
Jobs that are not good use cases
- Low-volume work. A task done a few times a month saves little once automated and still needs upkeep.
- Work with no system behind it. If the facts live only in an experienced employee's head, the agent can only guess.
- Work with no countable result. If nobody can say whether a unit was done correctly, nobody can improve it or pay for it fairly.
How to pick your first one
List the jobs your team repeats daily. For each, write down the system the facts live in and how you would count a finished unit. The job with the highest volume and the clearest count goes first. If your job is not on this page but meets the four conditions, it is done the same way. For the choice between an agent and a fixed workflow, see AI agent vs workflow.
Send us the job in one line and the free plan maps it within two working days.