Click “Agents” on the left sidebar. This will take you to a list of the existing agents for your org. To create a new one, click “New agent” in the top-right corner.

  • Agent name: The name of the agent is used to reference it elsewhere in Console, so you should pick something that’s easily identifiable. You can enter “Weather agent” here.

  • Agent description (optional): This description is displayed for extra context on the agent list screen you just saw. For this agent you can enter “An agent that can answer questions about the weather” here.

  • Prompt: The prompt that the agent will use for the LLM. Select your Weather prompt here.

  • Message: The message that the agent will deliver to the user at the beginning of a conversation. Select your Weather greeting here.

  • Timezone: The agent’s home timezone. You can select your local timezone here.

  • Speech-to-text: The speech-to-text provider that the agent will use to interpret user input in voice conversations. You can select Google STT V2 here.

  • Languages (optional): If you have configured a language group, you can select it here to provide the agent access to the language group’s languages and voices. You can skip this field for the tutorial.

  • Busy sound: The sound that will be played to the user in voice conversations if the LLM takes more than a threshold amount of time to return a response to user input. You can select Keyboard 1 here.

  • Label (optional): Labels are used for filtering agents on the agent list screen. You can skip this field for the tutorial.

  • Tool configuration: You can use this section to override default tool static parameter values at the agent level. You can skip it for the tutorial.

  • Session configuration: You can use this section to set other agent-level configuration values. You can skip it for the tutorial.

Click Save to save the agent.

You should now see a chat box to the right where you can test your new agent! Enter something like “hello” and you should see your greeting message.

From here, you can try asking for weather in a specific location, or ask general weather questions, and the agent should be able to answer them.

This concludes the tutorial! If you want to explore more of Syllable’s functionality with your new agent, you could try:

  • Creating a voice channel for your agent so you can call a phone number to speak to it

  • Updating your message to use time-based rules to display different greetings in the morning and afternoon

  • Create a language group, link it to your agent, and add the corresponding DTMF menu to the message to enable it to use different languages and voices

Create a messageAgents