Quickstart
Follow this guide to prepare your agent for testing
Before you begin, make sure you’ve signed up for an account. You can find detailed instructions here.
If you already have an agent set up and working, and are just looking for information on maintaining it, visit the maintenance guide.
Creating an agent
Start the creation process
After logging in, click “Create agent” to start the process.
You can also duplicate an existing agent from the home page by clicking the three dots information icon next to a profile.
The duplicated profile will have the same name as the original, but appended with (copy)
. You can also export and import existing agents as .bin
files.
Set a name, response language, voice, and greeting line
Full page: Voice, Agent settings
Set the general information for the agent, including agent name, response language, voice, and the welcome greeting.
After completing these steps, click “Next”.
Choose a language model
Go to Settings → Model to select which LLM will power your agent. The default is GPT-4o Mini, but others like Claude 3.5 Haiku or PolyLLM are also available depending on use case.
Full page: Model Selection
Select personality, role, and additional info
Next, select the personality, role, and enter the additional info for your agent.
Any additional info will be included as part of your agent’s personality prompt, packaged together with the other fields in this section.
After completing these steps, click “Next”.
Select knowledge topics
Full page: Knowledge base
Knowledge refers to the information and context the agent will have access to.
You can configure Actions, RAG (retrieval-augmented generation), and inline messaging with the Knowledge Base UI.
[Optional] Select a number for telephony integration
Full page: Telephony Integration
You may buy a number or connect an existing number for your agent. You can also skip this step and return later.
[Advanced] Integrate functions into your knowledge base
Full page: Functions
What they do: Functions allow you to add dynamic, programmable behavior to your agent, and allow you to handle external API calls, retrieve specific data, and use that data to make decisions based on real-time context.
Example use case: An agent retrieving shipping information for a customer query about an order.
[Advanced] Add a flow to your project
Full page: Flows What they do: Flows are designed for managing multi-step conversations, like booking a table at a restaurant, resetting a password, or collecting feedback.
Example use case: A customer reservation flow for a restaurant, with steps to ask for the date, time, and number of people before confirming the booking, as well as handling any problems that might arise along the way.
Test your agent (web-chat, browser call, or phone)
Full page: Agent Chat You can test your agent without deploying by:
- Using the web chat interface
- Making an in-browser voice call using the phone icon
- Calling from a connected number
Publish your agent
Full page: Environments & versions Once you have completed setup:
- Publish your agent to the Sandbox for internal testing.
- Promote to Pre-release for user testing and QA.
- Finally, promote it to Live to once it production-ready.
Each environment can be linked to a separate phone number and has rollback capabilities.
By following these steps, you can create a personalized and effective agent tailored to your needs.
How does my agent work?
Full page: Processing order
Once your agent is setup, here is how it will process calls:
- Caller speaks: The agent receives the caller’s input as an audio stream.
- ASR Service: Transcribes the audio into text.
- LLM Service: Interprets the request and determines an appropriate response.
- TTS Service: Converts the response back into speech and delivers it to the caller.
This cycle allows for real-time, responsive interactions. For a deeper breakdown of processing steps, see the advanced conversation flow processing order page.
You can set a custom disclaimer message to precede the call using an alternate voice. You can also assign multiple voices to your agent using the Multi-voice UI under Voice settings. Voices can be distributed across calls by percentage.