Publish your help center, configure the agent, and start it answering, end to end
A customer-facing agent that answers from your published articles and hands off when it cannot.
The AI Customer Support Agentanswers your customers' questions on your public help center, in a conversation, without them waiting for a person. It answers only from the knowledge base articles you have published to that help center, and it shows the customer which article the answer came from. When it cannot answer confidently, or when the question crosses one of your guardrails, it stops and hands the conversation to your team as a ticket with the whole exchange attached.
Setting it up is three steps: publish the help center it sits on, configure how it should behave, then start the trial or add an agent. This article walks all three in order. It is worth doing them in that order, because each step is what makes the next one possible: the agent has nothing to answer from until your help center is live, and nothing to answer on until it is configured.
Three things to have ready.
The public surface the agent answers on, and the article set it answers from.
Your help center is the branded, customer-facing view of your knowledge base. It is also where the agent lives, so this step comes first. If your help center is already published, skim the article gates below and move on to step 2.
Go to Service, open the settings gear, and choose Help Center. The help center is off by default, so nothing is public until you turn it on here.
Pick the subdomainthat forms your help center's address. It is how the public portal resolves your organization, so choose something your customers will recognize. Add your logo, brand color, theme, and default language while you are here.
Flip Enable help center and save. Your public address starts resolving straight away, with whatever articles already clear the three gates below.
In Service → Knowledge, make sure the articles you want the agent to use are published, set to visibility: public, and verified. See Your Public Help Center and Authoring & Verifying KB Articles for the full walkthrough of each gate.
Instructions, tone, guardrails, handoff, and which articles it may use.
Open the AI Agent tab in the Service hub. Everything about how the agent behaves is set there, and every change applies to the next conversation, so you can adjust it while it is live. The defaults are deliberately cautious, so an agent you configure lightly errs toward handing off rather than guessing.
A 14-day trial for a deposit, or buy an agent outright.
With the help center published and the agent configured, the last step is to turn it on. You have two ways in, and both start from the same place in your billing settings.
Start the trial for a one-time $1.99 deposit. The agent runs for 14 days, and if you keep it, the deposit is credited to your first month, so the trial costs you nothing extra. The trial is limited to one per organization. This deposit is separate from the deposit on a Laureo plan trial, and paying one does not pay the other.
Add an agent for $59.99 per month, each. An annual price is available, and you can run more than one agent, each billed separately. See AI Customer Support Agent Add-on for the full price list.
Every agent includes 500 conversations a month. The allowance resets at the start of each month and unused conversations do not carry over. A conversation is counted the first time the agent answers, so a customer browsing your help center or a question the agent hands straight off never counts.
If a month runs long, buy an extra conversation credit pack. Purchased credits do not reset with the month and are drawn only after the month's included allowance is used. If you run out entirely, the agent stops answering and your help center falls back to article search, so customers can still find answers and still open a ticket.
Two minutes to confirm the whole chain works.
Visit your help center address in a private browser window, signed out. You should see your branding, your public articles, and the agent ready to take a question.
A good first test is a question whose answer sits in one specific published article. You are checking two things: that the agent answers, and that it cites the article you expected.
Then ask about pricing, or for a refund, with those guardrails on. The agent should stop and offer to pass you to a person, using the handoff message you wrote. A handoff here is the system working, not failing.
Ultra for the agent, Business and above for the help center it sits on.