> ## Documentation Index > Fetch the complete documentation index at: https://docs.waterr.ai/llms.txt > Use this file to discover all available pages before exploring further. # Overview > What Waterr AI is, how the pieces fit together, and where to go next in these docs. Waterr AI puts a live AI agent on a video call. The agent sees, listens and talks in real time. It runs a conversation you design, such as an interview, a sales call, an onboarding walkthrough or a support session. When the call ends, you get a transcript, a recording and an evaluation against the goals you set. You can build everything without code in **Creator Studio** at [waterr.ai](https://waterr.ai), or drive the same platform from your own product through the **REST API**. ## How it fits together Every call starts from a **scenario**. A scenario combines four things: > **[Persona](https://docs.waterr.ai/getting-started/personas.md)** > > Who the agent is: its name, role, demeanor, voice and avatar. > **[Meeting script](https://docs.waterr.ai/customization/meeting-script.md)** > > How the agent runs the conversation: the opening, the topics to cover and how to handle specific moments. > **[Capabilities](#what-the-agent-can-do)** > > What the agent can do during the call: search the web, use a knowledge base, present files, call your tools and more. > **[Goals](https://docs.waterr.ai/customization/post-meeting-evaluations.md)** > > What the call measures. The agent scores each participant against these goals after the call. Participants never see them. Then you **send the agent**. Share a link, schedule a time-bound invite or embed the agent on your website. The participant joins, the agent runs the call, and the results come back to you. **1. Create a scenario** Describe what you need in plain language or start from a template. Studio drafts the persona, script and goals for you. See [Creating scenarios](https://docs.waterr.ai/getting-started/creating-scenarios.md). **2. Send the agent** Share a link, schedule a session or embed the agent on your site. See [Send Agent](https://docs.waterr.ai/getting-started/send-agent.md). **3. Review the results** Read the transcript, watch the recording and check each participant's goal scores. See [Post-meeting evaluations](https://docs.waterr.ai/customization/post-meeting-evaluations.md). New here? The [Quickstart](https://docs.waterr.ai/getting-started/quickstart.md) walks you through your first scenario in about two minutes. For a glossary of every term, see [Core concepts](https://docs.waterr.ai/getting-started/core-concepts.md). ## Choose your path > **[Build in Creator Studio](https://docs.waterr.ai/getting-started/quickstart.md)** > > No code. Create scenarios, send agents and review results from the browser. Start here if you're running interviews, training or demos yourself. > **[Build with the API](https://docs.waterr.ai/api-reference/introduction.md)** > > Create meetings, personas and scenarios from your own backend. Then pull transcripts and analyses, or receive them through webhooks. ## What the agent can do Turn these on for each scenario. You can mix and match them. > **[Vision](https://docs.waterr.ai/capabilities/vision.md)** > > Sees the participant's camera and shared screen. > **[Multi-language](https://docs.waterr.ai/capabilities/multi-language.md)** > > Holds conversations in 50+ languages. > **[Deep thinking](https://docs.waterr.ai/capabilities/deep-thinking.md)** > > Reasons at length for complex conversations. > **[Web search](https://docs.waterr.ai/capabilities/web-search.md)** > > Looks up live information during the call. > **[Knowledge base](https://docs.waterr.ai/capabilities/knowledge-base.md)** > > Answers from files you attach to the scenario. > **[Present file](https://docs.waterr.ai/capabilities/present-file.md)** > > Shows a slide, PDF, image or video during the call. > **[Participant memory](https://docs.waterr.ai/capabilities/participant-memory.md)** > > Remembers the people it has talked to, across calls and agents. > **[Meeting skills](https://docs.waterr.ai/capabilities/meeting-skills.md)** > > Loads guided instruction packs when it needs them. > **[Custom functions](https://docs.waterr.ai/capabilities/custom-functions.md)** > > Calls your own tools on your server or in the visitor's browser. > **[Multi-agent](https://docs.waterr.ai/capabilities/multi-agent.md)** > > Runs several agents in one meeting and hands off between them. > **[In-call chat](https://docs.waterr.ai/capabilities/in-call-chat.md)** > > Text chat and file uploads alongside the voice conversation. > **[Page tools](https://docs.waterr.ai/api-reference/page-tools.md)** > > Scrolls to and highlights parts of your web page while it talks. ## Put the agent in front of people > **[Shareable links](https://docs.waterr.ai/sharing/links.md)** > > Send a link through any channel. The participant opens it and the agent takes the call. > **[Scheduling](https://docs.waterr.ai/sharing/scheduling.md)** > > Send time-bound invites that only work during a set window. > **[Embed in your website](https://docs.waterr.ai/sharing/embed-in-website.md)** > > Add the agent to your site, app or LMS as a widget. > **[Booking page](https://docs.waterr.ai/sharing/booking-page.md)** > > Let participants book their own sessions. ## Make it yours > **[Participant experience](https://docs.waterr.ai/customization/participant-experience.md)** > > Choose what participants see and can do. > **[Personalization tokens](https://docs.waterr.ai/customization/personalization-tokens.md)** > > Put each participant's name and email into the script. > **[White label](https://docs.waterr.ai/customization/white-label.md)** > > Replace Waterr branding with your own. ## Build on the platform > **[API quickstart](https://docs.waterr.ai/api-reference/quickstart.md)** > > Get a live AI meeting with two API calls. > **[Bring your own agent](https://docs.waterr.ai/api-reference/bring-your-own-agent.md)** > > Point your OpenAI-compatible agent at Waterr, and it joins the call as the persona. > **[MCP server](https://docs.waterr.ai/api-reference/mcp.md)** > > Connect Waterr to Claude, ChatGPT, Cursor and other MCP clients. > **[Webhooks](https://docs.waterr.ai/api-reference/webhooks.md)** > > Receive signed events as soon as meetings end and analyses are ready. > **[Observability](https://docs.waterr.ai/api-reference/observability.md)** > > Stream speech, LLM and token traces to your OpenTelemetry backend. > **[Coding-agent skills](https://docs.waterr.ai/skills/claude-code.md)** > > Give Claude Code or Codex built-in knowledge of the Waterr API. ## Security and privacy Participants can be shown a [consent notice](https://docs.waterr.ai/security/consent.md) before they join. Data is [encrypted in transit and at rest](https://docs.waterr.ai/security/data-encryption.md). To learn how participant data is handled, see [Privacy](https://docs.waterr.ai/security/privacy.md). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.