> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://poly-ai.ferndocs.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://poly-ai.ferndocs.com/_mcp/server.

# Quickstart

> Create an account, build your first agent, and deploy it in minutes.

> **Note**
>
> This quickstart uses [Studio Assistant](/agent-studio/studio-assistant/overview) to scaffold the agent, then Web Calling to embed it. Available to project admins on enterprise clusters and to free-trial accounts. Free-trial users can switch to the full enterprise quickstart via the **Free trial — exit** pill.

The fastest path from sign-up to a working voice agent on your site. Studio Assistant does most of the building: you describe what you want, and it scaffolds flows, knowledge, voice, and integrations for you.

#### Create your account (\~1 min)

Go to [studio.poly.ai](https://studio.poly.ai/) and sign up with your email or Google account. No sales call to start.

![PolyAI sign-up page with email form and Google SSO option](/_fern-files/_img/fd92a930e84a681b79e412e09820df4ae29aef3bdbbac38460347d8a4e3765f2.webp)

You land on the Agent Studio home page. Studio Assistant asks for your company's website. Paste a URL and it starts building a tailored agent immediately.

![Agent Studio onboarding screen asking for your company website URL](/_fern-files/_img/cbaa4f692ec2b32359311f392a8a623cf742da785f8fd3179d5a6025a26a886f.webp)

The platform is self-serve from here. No billing, no metering, no contract.

#### Describe your agent (\~3 min)

Tell Studio Assistant what you want to build. A URL, a document, or a sentence describing the business is enough to get started.

Example prompts:

* `Build a reservations agent for a restaurant. Take name, party size, date, and time, then confirm.`
* `Read https://example.com and build an agent that answers questions about the company.`
* `I run a clinic. Build an agent that handles appointment requests and FAQ about opening hours.`

Studio Assistant reads your website, asks a few clarifying questions, then proposes a full agent plan: flows, knowledge, voice, and integrations. Review the plan and click **Approve**.

![Studio Assistant researching a website and planning a new voice agent](/_fern-files/_img/ea9403fac76c1b123723cc7ec87fa96a94256221c0d813e8189b5edf36a0068d.webp)

![Studio Assistant asking interactive questions about the agent's capabilities](/_fern-files/_img/15856ad84d7a6b4a4a19689c29214cb94438106a1bef083bb9cdd116b94116e5.webp)

![Agent plan card with Revise and Approve buttons](/_fern-files/_img/0f12e23aec05e2e6feafe74a73f79d8a8f15c971e2fede191500c403271f93ff.webp)

See [Prompting Studio Assistant](/agent-studio/studio-assistant/prompting-guide) for prompt patterns that work well.

#### Refine knowledge and behavior (\~3 min)

Studio Assistant will have populated **Knowledge > FAQs** based on what you gave it. Open it and skim:

* **Topics**: each is a question/answer pair grouped by intent. Edit any topic to tighten the answer or add sample utterances.
* **Sources**: upload extra PDFs or paste URLs to expand the knowledge base. Studio Assistant turns them into topics automatically.

Ask Studio Assistant to make changes in plain language, *"add a topic for refund policy"*, *"make the welcome message warmer"*, *"don't quote prices"*. It edits the agent for you.

![Adding a knowledge base topic in Agent Studio](/_fern-files/_img/c7c781bf88073ac23c3e295ae927bb0856282e67b71628c0fa1b93c2fa95a051.webp)

Changes stay as **Drafts** until you publish to **Sandbox** for testing.

#### Test in-browser (\~2 min)

#### In-browser call

The fastest way to test. Uses your device's microphone over WebRTC. No number to dial, no app to install.

1. Click **Test** in the top-right corner to open the **Agent Debugging** side panel
2. Choose **Call agent** under **Voice**
3. Select **Sandbox** from the environment dropdown
4. Begin speaking to your agent

![Call agent side panel with environment set to Sandbox and a Start test call button](/_fern-files/_img/ea2ea3bce9acc73f276c6362c581a2f5043fefa4a3be681a69d9ba775ca46177.webp)

#### Webchat preview

Test with text-based chat directly from Agent Studio.

1. Click **Test** in the top-right corner
2. Choose **Webchat** under **Messaging** (or **Chat with agent** to debug a voice agent via text)

The chat panel shows matched topics and tool calls alongside the conversation. Click the gear icon to toggle them.

![Test agent chat side panel showing matched topics and agent response](/_fern-files/_img/1a9fa2135a5f643194130072c390874351240fa549f1958a6e9574e40e4621bf.webp)

Every test conversation lands in [Conversations](/agent-studio/conversations/overview). Read the transcript, check what topics matched, and ask Studio Assistant to fix anything the agent got wrong.

#### Embed or share (\~1 min)

Publish your agent and put it in front of users.

#### Web Calling widget

Embed a click-to-call voice widget on any website. WebRTC end-to-end, no number to dial, no app to install.

1. Go to **Widgets** in the sidebar
2. Copy the embed snippet
3. Paste it into your site's HTML

See [Web Calling](/agent-studio/widgets/web-calling) for styling, behavior, and channel-mix options.

#### WebRTC share link

Share the agent without embedding by sending the WebRTC link from the in-browser call panel. Anyone with the link can talk to your agent in their browser.

Promote through environments when you're ready:

1. Go to **Deployments** in the sidebar
2. Click **Promote to Live** to make the current Sandbox build production-ready

Some projects use a simplified pipeline that promotes directly from Sandbox to Live. You can roll back to any previous version. See the [deployment pipeline guide](/agent-studio/deployments/overview) for details.

## Next steps

#### [Master Studio Assistant](/agent-studio/studio-assistant/prompting-guide)

Prompt patterns and the plan-review workflow.

#### [Embed Web Calling](/agent-studio/widgets/web-calling)

Voice widget setup, channel-mix matrix, and styling.

#### [Build flows](/agent-studio/flows/overview)

Multi-step workflows for bookings, forms, and structured tasks.

#### [Build locally with the ADK](/advanced/extend-with-code/adk)

Pull your project as YAML and Python, edit anywhere, push back.

Create an account, build an agent, add knowledge, test it, and deploy. Five steps.

> **Tip**
>
> **Project admin?** [Studio Assistant](/agent-studio/studio-assistant/overview) (Beta, admin-only) is the fastest way to scaffold an agent — describe what you want and it generates flows, topics, entities, and settings on a branch you can review. The manual steps below still work for any role.

## Prerequisites

* A use case in mind (e.g., customer support, reservations, FAQ)

#### Create your account (\~1 min)

Go to the [sign-up page](https://studio.us.poly.ai/) and create your PolyAI account.

#### Google SSO

1. Click **"Sign up with Google"**
2. Select your Google account or enter your credentials
3. Click **"Continue"** to authorize PolyAI

![Google SSO sign-up screen](/_fern-files/_img/bed8fc2ba9f020d84891c52e5351b16b157c7e867a80f09b1f9797c5c3bb2516.webp)

#### Email and password

1. Enter your **first name**, **last name**, and **email address**
2. Create a password (at least 12 characters, with 3 of 4 character types: lowercase, uppercase, numbers, special characters)
3. Click **"Create account"** and verify your email

![Email and password sign-up form](/_fern-files/_img/fd92a930e84a681b79e412e09820df4ae29aef3bdbbac38460347d8a4e3765f2.webp)

Once signed in, you'll land on the Agent Studio home page.

#### Create your agent (\~2 min)

From the home page, click **+ Agent** to start the agent creation wizard. You can create a blank agent or import an existing configuration.

Configure the basics:

* **Agent name**, internal identifier for your project
* **Response language**, primary language for responses (see [multilingual support](/agent-studio/behavior/language/multi-language) for additional languages)
* **Voice**, select from available [text-to-speech (TTS)](https://en.wikipedia.org/wiki/Speech_synthesis) voices
* **Welcome greeting**, first message users receive (can be customized later in [agent settings](/agent-studio/behavior/general/personality-and-role))

Click **Next** to enter Agent Studio.

![Agent creation wizard with name, language, voice, and greeting fields](/_fern-files/_img/bc445ce631120b02f59cb31973766bc7a7b70c4fb3c1af77e0f09bc6539dcb7a.webp)

You can also duplicate an existing agent by clicking the three-dot menu next to any agent on the home page.

#### Add knowledge (\~5 min)

Navigate to **Knowledge > FAQs** in the sidebar.

Click **Add topic** and provide:

* **Topic name**, what this topic covers (e.g., "Store hours")
* **Sample questions**, up to 20 ways users might ask (e.g., "When are you open?")
* **Answer**, the response your agent should give

Click **Save** to create the topic.

![Adding a knowledge base topic in Agent Studio](/_fern-files/_img/c7c781bf88073ac23c3e295ae927bb0856282e67b71628c0fa1b93c2fa95a051.webp)

Changes are saved as **Drafts**. Publish to **Sandbox** to test them. Learn more about [environments and versions](/agent-studio/deployments/overview).

**Optional:** Add more topics to expand your agent's capabilities. You can also:

* Upload PDFs or URLs to auto-generate topics
* Connect external knowledge sources like [Zendesk](/integrations/crm/zendesk-talk) or [Google Sheets](/integrations/managed-services/data-and-utilities/google-sheets) using the [Connected tab](/agent-studio/knowledge/sources/sources) in Knowledge
* Add [actions](/agent-studio/knowledge/fa-qs/actions/overview) to trigger handoffs, SMS, or other behaviors

See the full [FAQs guide](/agent-studio/knowledge/fa-qs/fa-qs) for details on how [RAG](/agent-studio/knowledge/fa-qs/rag) (retrieval-augmented generation) powers topic matching.

#### Test your agent (\~2 min)

#### In-browser call

The fastest way to test, uses your device's microphone directly.

1. Click the **phone icon**  in the top-right corner
2. Select **Sandbox** from the environment dropdown
3. Begin speaking to your agent

![In-browser call test panel](/_fern-files/_img/269589523811374a22c837eee8b1f56d6250a7f47f34c20f8ee28190b54c9cd5.webp)

#### Webchat

Test with text-based chat, directly from Agent Studio.

1. Go to the agent main page
2. Click the **webchat icon** to open a text-based conversation

The chat window shows tool calls and topic citations alongside the conversation. Click the Settings icon to toggle these.

![Webchat interface showing tool calls and topic citations](/_fern-files/_img/122086d42f584fab9e043307c946e59ac62af46518c79147f2110514f5d84302.webp)

See [webchat setup](/agent-studio/messaging/overview) for more details.

#### Phone

Test in a production-like environment by calling a connected number.

1. Go to **Voice > Numbers** in the sidebar
2. Click **"Add number"** to purchase a number or connect an existing one
3. Call the number to speak with your agent

See [Numbers](/agent-studio/voice/numbers/overview) for setup instructions.

**Testing tips:**

* Use specific keywords to trigger your agent's topics
* Test with different accents and speaking styles
* For [multilingual agents](/agent-studio/behavior/language/multi-language), switch languages mid-conversation to test detection
* Review conversations in the [Conversations dashboard](/agent-studio/conversations/overview) after testing

#### Deploy to production (\~1 min)

Promote your agent through the deployment pipeline:

1. Go to **Deployments** in the sidebar
2. Click **Promote to Pre-release** for user acceptance testing (if available in your project)
3. Click **Promote to Live** to make your agent production-ready

Each environment can have its own phone number and configuration.

![Deployment pipeline showing Sandbox to Live promotion](/_fern-files/_img/e4344ebcfbedd37323b978551915234040c87b3f9af5dc21c08b5121197a657b.webp)

Some projects use a simplified pipeline that promotes directly from Sandbox to Live, skipping Pre-release. You can roll back to any previous version if issues arise, see the [deployment pipeline guide](/agent-studio/deployments/overview) for details.

## Next steps

#### [Add advanced features](/agent-studio/tools/overview)

Connect APIs and add dynamic behavior with Python functions

#### [Build conversation flows](/agent-studio/flows/overview)

Multi-step workflows for bookings, forms, and structured tasks

#### [Configure voice settings](/agent-studio/voice/overview)

TTS, voice selection, and audio settings

#### [Monitor performance](/agent-studio/custom-dashboards/overview)

Dashboards, conversation review, and metrics

## How your agent works

Each conversation turn follows a pipeline: **ASR** (speech to text) → **LLM** (knowledge retrieval and response generation) → **TTS** (text to speech). See [architecture](/academy/glossary/architecture-overview) for a detailed breakdown, or [processing order](/academy/glossary/conversation-flow) for the step-by-step flow.