Skip to main content
Each agent lives in a project. In the dashboard, the New project wizard creates the project and its first agent in three steps. The API creates the agent and its project in one request.

​
Prerequisites

Before you begin:

​
Create the agent

1

Start building an agent

This guide builds an agent that runs on the SLNG orchestrator. To run the agent in your own code on LiveKit, Pipecat, or a custom client instead, see Improve an agent.
On the Projects page, click New project, then click Start building on the Build an agent card.
New project step 1 with the Build an agent card

The first step of New project. Choose Build an agent.

2

Pick a template

Templates prefill the pipeline, prompt, and voice for an industry. You can change any of it later.
Keep From scratch to choose every piece yourself, or select a template such as Healthcare or Insurance. Click Continue.
New project step 2 with From scratch selected and four industry templates

Start from scratch or from an industry template.

3

Name the project and choose a region

Pick the region closest to your callers. Region sets the latency floor for every turn of the conversation and filters which models you can use.
On the Configure your project step, enter a Project name, then open the Region dropdown and pick where the project lives. SLNG places the agent in an agent region there.
Configure your project step with the Region dropdown open

The Region selector on the Configure your project step.

4

Choose a language and create

The primary language filters models to the ones that support it and sets the default speech to text and text to speech choices.
Open the Primary language dropdown, pick the language your callers speak, then click Create project.
Configure your project step with the Primary language dropdown open

Primary language selector and the Create project button.

The wizard closes and opens the new project on its Listen section.

​
What you have now

A project with a linked agent that has a name, a region, a language, and default models. It cannot take a call yet. The agent still needs its three sections configured, and the project page opens on the first one.

​
Update an agent

In the dashboard, open the project and change the agent in its Listen, Think, or Speak section. Through the API, send a PATCH to /v1/agents/{agent_id} with only the fields you want to change. Use the id you kept from the create response.
Request
Top-level fields such as greeting update on their own. The models object is the exception: a PATCH replaces it as a unit, so send the whole block, including stt, llm, tts, and tts_voice, even when you change one value. The Listen, Think, and Speak guides each show the models body for their own fields. To replace the complete configuration in one request, send it with PUT. This is how you change tool_refs and mcp_refs, which a PATCH rejects: download the configuration, edit it, and send it back. See Attach a tool to an agent.

​
Next steps

Configure the agent’s three sections, in this order:
  1. Listen: the speech to text model and how the agent hears callers.
  2. Think: the system prompt, greeting, and language model.
  3. Speak: the text to speech model and voice.
Once Speak is done, the project page offers a test session.