How it fits together
Every call starts from a scenario. A scenario combines four things:Persona
Who the agent is: its name, role, demeanor, voice and avatar.
Meeting script
How the agent runs the conversation: the opening, the topics to cover and how to handle specific moments.
Capabilities
What the agent can do during the call: search the web, use a knowledge base, present files, call your tools and more.
Goals
What the call measures. The agent scores each participant against these goals after the call. Participants never see them.
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.
2
Send the agent
Share a link, schedule a session or embed the agent on your site. See Send Agent.
3
Review the results
Read the transcript, watch the recording and check each participant’s goal scores. See Post-meeting evaluations.
Choose your path
Build in Creator Studio
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
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
Sees the participant’s camera and shared screen.
Multi-language
Holds conversations in 50+ languages.
Deep thinking
Reasons at length for complex conversations.
Web search
Looks up live information during the call.
Knowledge base
Answers from files you attach to the scenario.
Present file
Shows a slide, PDF, image or video during the call.
Participant memory
Remembers the people it has talked to, across calls and agents.
Meeting skills
Loads guided instruction packs when it needs them.
Custom functions
Calls your own tools on your server or in the visitor’s browser.
Multi-agent
Runs several agents in one meeting and hands off between them.
In-call chat
Text chat and file uploads alongside the voice conversation.
Page tools
Scrolls to and highlights parts of your web page while it talks.
Put the agent in front of people
Shareable links
Send a link through any channel. The participant opens it and the agent takes the call.
Scheduling
Send time-bound invites that only work during a set window.
Embed in your website
Add the agent to your site, app or LMS as a widget.
Booking page
Let participants book their own sessions.
Make it yours
Participant experience
Choose what participants see and can do.
Personalization tokens
Put each participant’s name and email into the script.
White label
Replace Waterr branding with your own.
Build on the platform
API quickstart
Get a live AI meeting with two API calls.
Bring your own agent
Point your OpenAI-compatible agent at Waterr, and it joins the call as the persona.
MCP server
Connect Waterr to Claude, ChatGPT, Cursor and other MCP clients.
Webhooks
Receive signed events as soon as meetings end and analyses are ready.
Observability
Stream speech, LLM and token traces to your OpenTelemetry backend.
Coding-agent skills
Give Claude Code or Codex built-in knowledge of the Waterr API.