The brand holds the knowledge
A voice agent has no knowledge base of its own, and it does not borrow one from a chatbot either. It answers from its brand — everything on Brand → Knowledge and Brand → Products: knowledge bases, documentation, uploaded files, website pages Yaplet has read for you, question-and-answer entries and your product catalogue.
That is exactly the same material the brand's chat AI reads. There is no linking step, no picker, and no separate voice copy to keep up to date. If you are looking for a "Vex chatbot" field on the agent's Connections tab, it is gone — the brand answers that question now.
What the agent can do on a call
A voice agent is given a small, deliberate set of abilities:
- Look something up in the brand's knowledge. Offered whenever the brand actually has something indexed. The agent is told to use it for anything that could plausibly be company-specific — products, pricing, services, policies, opening hours, contact details — and to prefer looking up and finding nothing over refusing to look.
- End the call. Always available.
- Run one of your scripted workflows, or call one of your API tools. Only when the brand also has a Vex AI chat agent. See the restriction below.
What it cannot do, including telling the time
Older versions of this article described built-in tools that read the caller's phone number, the call duration and your business hours. Those do not exist, and never did. Specifically:
- The agent has no clock. Nothing gives it the current time or date, and its instructions explicitly treat "what time is it" as small talk to answer casually rather than look up.
- It has no business-hours tool. If you want it to know your opening hours, they have to be either written into its prompt or published as an article it can find.
- It cannot hand the caller to a person. There is no live transfer.
What happens when a caller asks something
| Caller asks | What the agent does |
|---|---|
| "What are your shipping zones?" | Looks it up in the brand's knowledge and answers from what it finds. |
| "Are you open right now?" | Looks it up. It answers well only if your opening hours are published as an article — there is no hours tool and no clock. |
| "Where is my order?" | Needs one of your API tools, which needs the brand to also have a Vex chat AI. Without that, the agent can only say it cannot check. |
| "Hi, how are you?" | Answers directly. Greetings and small talk deliberately skip the lookup. |
| Something covered in the agent's prompt | Answers directly from the prompt, with no lookup. |
The one real restriction
Workflows and API tools are offered on a call only when the brand has a Vex chat AI as well. Knowledge lookup and ending the call always work.
Most people never run into this, because a brand with phone agents usually has a Vex too. But a brand set up deliberately as phone-only will be able to look things up and nothing more — no scripted workflows on calls, no API tools. There is a second consequence worth knowing: those calls are billed and transcribed exactly as normal, but they do not appear in the AI answer-quality reports, because those figures are kept per chat AI.
Two more conditions apply to workflows specifically. A workflow only runs on a call if its trigger is User says, and if none of its steps rule out phone calls — a form, a link, buttons, a reply-time step, a request-agent step, collect-data or ask-a-question all do. The Channels column on Brand → Workflows tells you which of your scripts qualify.
What makes good voice knowledge
The same articles serve chat and phone, but a few habits make a real difference when the words are spoken:
- One canonical answer per topic. Three overlapping articles on the same question make the agent hesitate while it picks. Merge them.
- Spell out abbreviations. The agent reads what you wrote. "U.S. Postal Service" sounds like a company; "USPS" sounds like four letters.
- Lead with a one-sentence answer. The agent is instructed to reply in at most two sentences unless the caller asks for more, so it will use your opening line and drop the rest. Make that first line the answer.
- Go easy on lists. Heavily structured bullet points come out as a recital. Smooth prose sounds like a person.
If callers say the agent is vague on basic questions, the usual cause is a fragmented knowledge base — lots of short overlapping articles competing for the same query. Consolidating into one clear article per topic fixes it more reliably than rewriting the prompt.
When the agent's language differs from your content's
The agent writes its search in the language you configured on it, and Yaplet translates that search into the language your material is written in before looking anything up. So an agent set to Hungarian can answer from an English knowledge base without you doing anything. This is keyed on the agent's language setting, not on what the caller happens to speak, and the spoken reply always comes back in that same configured language.
What is stored, and what is masked
Both halves of the call are saved — the caller's side and the agent's replies — as a conversation in your inbox. If the brand has Privacy masking switched on at Brand settings → Advanced, email addresses, phone numbers and card numbers are stripped from that stored transcript and from the call's inbox messages.
Be clear about what that does and does not mean on the phone. It hides those details in what Yaplet keeps. It cannot hide them from the AI during the call, because the caller's speech reaches the AI as they say it. It is best-effort rather than a guarantee — if the masking service is slow or down, the conversation goes through unmasked and nothing logs that it happened — and it does not change conversations recorded before you switched it on.
Updating knowledge once, for every channel
Because it is one brand's knowledge, publishing an article makes it available everywhere at once: the chat AI uses it on the next message, the voice agent on the next call, the inbox on the next suggested reply, and AI social posting the next time it writes. You never maintain a separate copy for voice.
One signal to watch for: on Brand → Voice, an agent's card warns "This brand has no indexed knowledge — calls will be answered from general knowledge only." If you see that, the agent is answering the phone with nothing behind it.
What to read next
To add or check the material itself, see Add knowledge to your brand. To handle calls outside your working hours, see Set business hours for a phone number.