Skip to main content
One agent serves every channel. This page covers how it decides what to do and what you can change about that. It is also stateful: before it decides anything, it loads that customer’s accumulated state from every prior conversation, every channel and every connected system. That is a big enough subject to have its own page, and it is the thing most worth understanding about how Vorel behaves.

Memory and state

What the agent remembers, how identity resolves across channels, and how facts carry provenance.

​
Routing and sub-agents

A turn is not handled by one large prompt. The agent first works out what the customer wants, then hands the turn to a specialist: Each sub-agent has a narrower prompt and a smaller tool set than a single general agent would. This is why behaviour is easier to constrain: the booking specialist cannot answer a clinical question, and the knowledge specialist cannot invent an appointment. Common, unambiguous intents resolve without a model call at all, which is most of the latency saving on voice.

​
Tools

Tools are the only way the agent touches anything real. The agent cannot state a booking exists without the booking tool having succeeded. This is enforced, not just prompted. See Guardrails.

​
Controlling the tool surface

Under Settings, then Tools you choose which tools the agent may use. Turning off CRM write, for example, makes the agent read your CRM without ever creating records in it. Tools are also scoped per channel where a channel cannot support them. See Channels overview.

​
What you configure

Persona

Name, tone, signature phrases, and how formal it should be, in English and Arabic.

Hours

Working hours, holidays and timezone. The agent answers differently outside hours.

Call goals

What a successful conversation looks like, which is what qualification works towards.

Handoff rules

What must always reach a human. See Routing and escalation.

Macros

Canned responses your team can use in the inbox.

Guardrails

Forbidden phrases and how strictly answers are graded.

​
Agent releases

Configuration changes can be captured as an immutable snapshot and promoted through stages rather than edited live. A snapshot records the persona, prompts, rules and tool set as they were at that moment, so you can compare two versions, promote one, and roll back to the previous one if a change made things worse.

​
Experiments

You can run two prompt variants against real traffic on a split and compare their quality scores, rather than changing a prompt and hoping. Results appear in Quality.

​
What the agent will not do

  • Answer from general world knowledge when your knowledge base has nothing. It says it does not know and offers to get a person.
  • Promise an appointment without checking availability.
  • Quote a price that is not in your catalog or a tool result.
  • Use a phrase on your forbidden list.

Knowledge

What the agent answers from.

Customer memory

What it remembers between conversations.

Booking

How appointments are made.

Explainability

Why it said what it said.