1. Create an assistant
1
Open Assistants and click 'New assistant'
The Create assistant modal opens. Enter a name your team will recognize, e.g.
Reception EN.2
Choose the agent type
- Single prompt — free-form conversations from one system prompt (best for most first assistants).
- Conversational flow — visual flow builder for branches, data collection, and transfers.
3
Pick a template (or build from scratch)
Use Build from scratch, or apply a catalog template (filter by theme). Templates copy into the system prompt and optional first message — they are not live-linked.
4
Edit greeting and instructions
In the editor:
- Prompt mode: greeting + system prompt on the canvas. Use Choose template anytime.
- Flow mode: open the flow builder; the base instructions live under Settings → General → Advanced prompt (also collapsed on the canvas).
5
Pick a voice and models — or keep the defaults
The defaults (a low-latency pipeline with a recommended voice) work well out of the box. You can browse the voice library later and preview voices before switching.
6
Save
Your assistant is now ready to take calls.
2. Test it in the browser
Every assistant can be tested directly from the editor — same engine, same models, no telephony involved. Click the Test button in the editor header and pick a channel:- Call — a live voice call in the browser:
- Allow microphone access.
- Talk to your assistant. Interrupt it mid-sentence — it should stop and listen.
- End the call, then open Calls to review the transcript.
- Chat — a text-only session with the same prompt, flow, tools and knowledge base. Perfect for quickly iterating on prompts without speaking out loud.
3. Put it on a phone number
When the web call sounds right:- Buy a number in Phone numbers and assign the assistant to it — inbound calls are answered immediately.
- Or connect your own SIP trunk (BYO SIP) to use existing numbers.
- For outbound, start a single test call from the assistant page or set up a campaign.
Next steps
System prompt vs. flow builder
When a single prompt is enough — and when to switch to a visual flow.
Conversation quality
Background audio, interruption handling, filler phrases, guardrails.
Knowledge base
Let the assistant answer from your documents.
Engine modes
Pipeline, realtime, and half-cascade explained.