# Waterr.ai

- [Overview](https://docs.waterr.ai/overview.md): What Waterr AI is, how the pieces fit together, and where to go next in these docs.
- [Core Concepts](https://docs.waterr.ai/getting-started/core-concepts.md): Quick reference for the key building blocks of Waterr Meet.
- [Quickstart](https://docs.waterr.ai/getting-started/quickstart.md): Create your first AI scenario in under 2 minutes.
- [Creating Scenarios](https://docs.waterr.ai/getting-started/creating-scenarios.md): Create AI-powered conversation scenarios from scratch or using templates.
- [Understanding AI Personas](https://docs.waterr.ai/getting-started/personas.md): Configure the AI character your participants interact with.
- [Send Agent](https://docs.waterr.ai/getting-started/send-agent.md): Send an AI agent to run a meeting for you — share a link or schedule a time-bound invite.
- [Vision](https://docs.waterr.ai/capabilities/vision.md): Enable your AI persona to see and understand participants through camera and screen sharing.
- [Multi-Language](https://docs.waterr.ai/capabilities/multi-language.md): Run AI conversations in 50+ languages with automatic detection and translation.
- [Deep Thinking](https://docs.waterr.ai/capabilities/deep-thinking.md): Enable extended reasoning for complex, nuanced AI conversations.
- [Meeting Skills](https://docs.waterr.ai/capabilities/meeting-skills.md): Give your AI agent invokable, revokable instruction packs — guided flows it loads on demand and drops when done.
- [Web Search](https://docs.waterr.ai/capabilities/web-search.md): Let your AI persona search the web during conversations for real-time information.
- [Memory](https://docs.waterr.ai/capabilities/participant-memory.md): Let your agents remember the people they talk to — shared across agents by a user_memory_tag, and importable from the systems you already use.
- [Knowledge Base](https://docs.waterr.ai/capabilities/knowledge-base.md): Attach reference files to a scenario so the AI can pull from them mid-conversation.
- [Present File](https://docs.waterr.ai/capabilities/present-file.md): Let the AI show a slide, PDF, image, or video to the participant mid-meeting.
- [Screen Apps](https://docs.waterr.ai/capabilities/screen-apps.md): Let your AI persona put a booking page, a form, or any web page on the participant's screen at the right moment.
- [In-Call Chat](https://docs.waterr.ai/capabilities/in-call-chat.md): Text chat alongside the voice meeting — supports messages and file uploads the AI can read.
- [Multi-Agent](https://docs.waterr.ai/capabilities/multi-agent.md): Run multiple AI agents in the same meeting, with mid-call handoffs between them.
- [Custom Functions](https://docs.waterr.ai/capabilities/custom-functions.md): Attach your own tools to a scenario so the AI can call them mid-meeting — on your server, or inside your visitor's browser.
- [Consent](https://docs.waterr.ai/capabilities/consent.md): Show a custom consent message before the participant joins — for recording, data use, or any disclosure your team requires.
- [Social](https://docs.waterr.ai/capabilities/social.md): Connect social profiles to enrich AI conversations with participant context.
- [Notifications](https://docs.waterr.ai/capabilities/notifications.md): Get notified when sessions complete and receive results automatically.
- [Share Links](https://docs.waterr.ai/sharing/links.md): Generate and manage shareable session links.
- [Embed in Website](https://docs.waterr.ai/sharing/embed-in-website.md): Add an AI conversation widget directly to your website or LMS.
- [Scheduling](https://docs.waterr.ai/sharing/scheduling.md): Send time-bound invite links to specific participants.
- [Booking Page](https://docs.waterr.ai/sharing/booking-page.md): Let participants schedule their own sessions via a Cal.com booking page.
- [Meeting Script](https://docs.waterr.ai/customization/meeting-script.md): Write the script that controls how your AI persona behaves during a session.
- [Personalization Tokens](https://docs.waterr.ai/customization/personalization-tokens.md): Drop the participant's name and email into your meeting script and welcome message.
- [Post-Meeting Evaluations](https://docs.waterr.ai/customization/post-meeting-evaluations.md): Set up goals and scoring to automatically evaluate participants after each session.
- [Participant Experience](https://docs.waterr.ai/customization/participant-experience.md): Customize what participants see and how they interact during a session.
- [White Label](https://docs.waterr.ai/customization/white-label.md): Remove Waterr branding and use your own brand identity for participant-facing experiences.
- [Consent](https://docs.waterr.ai/security/consent.md): Configure consent prompts shown to participants before sessions begin.
- [Data Encryption](https://docs.waterr.ai/security/data-encryption.md): How Waterr Meet protects your data with encryption at rest and in transit.
- [Privacy](https://docs.waterr.ai/security/privacy.md): How Waterr Meet handles participant privacy and data protection.
- [Introduction](https://docs.waterr.ai/api-reference/introduction.md): Build AI meetings programmatically with the WaterrAI API.
- [Quick Start](https://docs.waterr.ai/api-reference/quickstart.md): Create your first AI meeting in 2 API calls
- [Authentication](https://docs.waterr.ai/api-reference/authentication.md): Create and manage API keys to authenticate with the WaterrAI API
- [Errors](https://docs.waterr.ai/api-reference/errors.md): Every error carries a stable type, a specific code, and a request id you can quote to support.
- [Rate limits](https://docs.waterr.ai/api-reference/rate-limits.md): Published limits, the headers that tell you where you stand, and how to back off.
- [Pagination](https://docs.waterr.ai/api-reference/pagination.md): Cursor pagination on list endpoints — opt in with `limit`, walk with `next_cursor`.
- [Idempotency](https://docs.waterr.ai/api-reference/idempotency.md): Retry writes safely — send an Idempotency-Key and a repeat replays the original response instead of doing the work twice.
- [Versioning](https://docs.waterr.ai/api-reference/versioning.md): What we promise not to change, what we may change, and how long you get to migrate.
- [Billing and credits](https://docs.waterr.ai/api-reference/billing.md): One credit balance for every call, chat, and model request. Plans, per-minute pricing, top-ups, and what the API returns when the balance runs out.
- [Changelog](https://docs.waterr.ai/api-reference/changelog.md): Every change to the public API, newest first.
- [Session Lifecycle](https://docs.waterr.ai/api-reference/session-lifecycle.md): Understand how a meeting session flows from creation to analysis.
- [Create a new meeting](https://docs.waterr.ai/api-reference/endpoint/post-meetings.md)
- [Get a meeting by ID](https://docs.waterr.ai/api-reference/endpoint/get-meetings-id.md)
- [Get all meetings](https://docs.waterr.ai/api-reference/endpoint/get-meetings.md)
- [End a meeting](https://docs.waterr.ai/api-reference/endpoint/put-meetings-meetingid-end.md)
- [Update a meeting](https://docs.waterr.ai/api-reference/endpoint/put-meetings-meetingid.md)
- [Delete a meeting](https://docs.waterr.ai/api-reference/endpoint/delete-meetings-meetingid.md)
- [Create a new scenario](https://docs.waterr.ai/api-reference/endpoint/post-scenarios.md)
- [Get all scenarios](https://docs.waterr.ai/api-reference/endpoint/get-scenarios.md)
- [Update a scenario](https://docs.waterr.ai/api-reference/endpoint/put-scenarios-id.md)
- [Delete a scenario](https://docs.waterr.ai/api-reference/endpoint/delete-scenarios-id.md)
- [Export a scenario as JSON](https://docs.waterr.ai/api-reference/endpoint/get-scenarios-id-export.md)
- [Get all meetings for all scenarios of a user](https://docs.waterr.ai/api-reference/endpoint/get-scenarios-membership-membershipid-meetings.md)
- [Create a new persona](https://docs.waterr.ai/api-reference/endpoint/post-personas.md)
- [Get a persona by ID](https://docs.waterr.ai/api-reference/endpoint/get-personas-id.md)
- [Get all personas](https://docs.waterr.ai/api-reference/endpoint/get-personas.md)
- [Update a persona](https://docs.waterr.ai/api-reference/endpoint/put-personas-id.md)
- [Delete a persona](https://docs.waterr.ai/api-reference/endpoint/delete-personas-id.md)
- [Tools (Custom Functions)](https://docs.waterr.ai/api-reference/custom-functions.md): Let the AI persona call your code mid-meeting — define once, attach to any scenario.
- [List tool definitions](https://docs.waterr.ai/api-reference/endpoint/get-custom-functions.md): Return every tool on your account, oldest first.
- [Create a tool definition](https://docs.waterr.ai/api-reference/endpoint/post-custom-functions.md): Register a tool on your account. Define once, then attach to any number of scenarios with [`Attach a tool to a scenario`](#tag/Scenario-Tools/operation/AttachToolToScenario). Editing the definition later ([`Update a tool`](#tag/Tools/operation/UpdateTool)) propagates to every attached scenario insta…
- [Get a tool definition](https://docs.waterr.ai/api-reference/endpoint/get-custom-functions-id.md): Fetch one tool definition by ID.
- [Update a tool definition](https://docs.waterr.ai/api-reference/endpoint/patch-custom-functions-id.md): Patch any subset of fields. Propagates to every attached scenario instantly. Sending a new `webhook_secret` is a rotation: the old one keeps verifying for 24 h. To have us mint the new secret instead, use `POST /custom-functions/{id}/rotate-secret`.
- [Delete a tool definition](https://docs.waterr.ai/api-reference/endpoint/delete-custom-functions-id.md): Permanently delete a tool. Cascades — every attachment to a scenario is removed too. Meetings already in flight finish normally.
- [Screen Apps](https://docs.waterr.ai/api-reference/screen-apps.md): Render your own UI on the presented screen — forms, pickers, calculators — and let the agent drive it.
- [Meeting Actions](https://docs.waterr.ai/api-reference/meeting-actions.md): Reach into a live call from your own server — make the agent say something, tell it something, or drive a screen app.
- [Live Meeting Events](https://docs.waterr.ai/api-reference/meeting-events.md): Know what is happening in a call while it runs — screen shares, cameras, what is on the stage — as webhooks or a pollable log.
- [Skill Packages](https://docs.waterr.ai/api-reference/skill-packages.md): Ship a skill as one file — instructions, tools, screen renderers and an events endpoint — and install it into a workspace in one call.
- [Embed API](https://docs.waterr.ai/api-reference/embed-tokens.md): Mint a short-lived signed JWT and get a ready-to-paste iframe snippet in one call.
- [Live Website Events](https://docs.waterr.ai/api-reference/live-website-events.md): Tell the assistant what the visitor is doing on your site, so it can answer about what's in front of them.
- [Page Tools](https://docs.waterr.ai/api-reference/page-tools.md): The assistant can scroll your page to a section and highlight a single element, so it can say "it's this one" instead of giving directions.
- [Memories](https://docs.waterr.ai/api-reference/memories.md): Read, import and delete what your agents remember, by user_memory_tag.
- [Add memories](https://docs.waterr.ai/api-reference/endpoint/post-memories.md): Add facts to a container — from another memory system, a CRM, or by hand. Each entry is one fact; a multi-line string becomes one memory per line. Facts already in the container (ignoring case, spacing and bullets) are skipped, so re-running an import is harmless.
- [List memories under a tag](https://docs.waterr.ai/api-reference/endpoint/get-memories.md): Every memory in one container, newest first — the order a call spends its token budget in.
- [List memory containers](https://docs.waterr.ai/api-reference/endpoint/get-memories-tags.md): Every user_memory_tag in your workspace that holds at least one memory, newest activity first.
- [Get a memory container](https://docs.waterr.ai/api-reference/endpoint/get-memories-tags-tag.md): The container summary plus every memory in it, newest first.
- [Get a memory](https://docs.waterr.ai/api-reference/endpoint/get-memories-id.md)
- [Update a memory](https://docs.waterr.ai/api-reference/endpoint/patch-memories-id.md): Correct a fact in place. content stays one fact on one line; an edit that duplicates another fact under the same tag is refused. The tag and source fields cannot change — to move a fact, delete it and add it under the other tag.
- [Delete a memory](https://docs.waterr.ai/api-reference/endpoint/delete-memories-id.md)
- [Delete a memory container](https://docs.waterr.ai/api-reference/endpoint/delete-memories-tags-tag.md): Forget every memory under the tag, for every agent that uses it.
- [Get analysis by meeting ID](https://docs.waterr.ai/api-reference/endpoint/get-analyses-meeting-meetingid.md)
- [Get an analysis by ID](https://docs.waterr.ai/api-reference/endpoint/get-analyses-id.md)
- [Trigger manual analysis for a meeting](https://docs.waterr.ai/api-reference/endpoint/post-analyses-trigger-meetingid.md)
- [Get transcripts by meeting ID](https://docs.waterr.ai/api-reference/endpoint/get-transcripts-meeting-meetingid.md)
- [Get a transcript by ID](https://docs.waterr.ai/api-reference/endpoint/get-transcripts-id.md)
- [Get recording CloudFront URL with thumbnail by Daily meeting ID](https://docs.waterr.ai/api-reference/endpoint/get-recordings-url-with-thumbnail-meetingid.md)
- [Get recordings by meeting ID](https://docs.waterr.ai/api-reference/endpoint/get-recordings-meeting-meetingid.md)
- [Goals](https://docs.waterr.ai/api-reference/goals.md): What a goal is, what it produces after a call, and when to reach for one.
- [Create a new goal](https://docs.waterr.ai/api-reference/endpoint/post-goals.md)
- [Get all goals](https://docs.waterr.ai/api-reference/endpoint/get-goals.md)
- [Update a goal](https://docs.waterr.ai/api-reference/endpoint/put-goals-id.md)
- [Delete a goal](https://docs.waterr.ai/api-reference/endpoint/delete-goals-id.md)
- [Avatars](https://docs.waterr.ai/api-reference/avatars.md): The persona's visual identity — pick from the curated catalog and assign it in one call.
- [List avatars](https://docs.waterr.ai/api-reference/endpoint/get-avatars.md): Return the avatar catalog — global curated avatars plus your own. Filter by category, gender, or source.
- [Get an avatar](https://docs.waterr.ai/api-reference/endpoint/get-avatars-id.md): Fetch a single avatar by ID.
- [Set a persona's avatar](https://docs.waterr.ai/api-reference/endpoint/put-personas-id-avatar.md): Assign a catalog avatar by `avatar_id` (or any hosted image by `url`) to a persona. Optionally sync the paired voice.
- [List available voices](https://docs.waterr.ai/api-reference/endpoint/get-voices.md): Return every voice available to the caller. Use the returned `id` as `voice_id` when creating personas or meetings.
- [Voice attributions](https://docs.waterr.ai/api-reference/voice-attributions.md): Sources and licenses for the voices used by the Waterr realtime speech engine.
- [Guardrails](https://docs.waterr.ai/api-reference/guardrails.md): Named rules appended to a scenario's system prompt — define once, attach to any scenario.
- [List guardrails](https://docs.waterr.ai/api-reference/endpoint/get-guardrails.md): Return every guardrail on your account, newest first.
- [Create a guardrail](https://docs.waterr.ai/api-reference/endpoint/post-guardrails.md): Register a guardrail on your account. Define once, then attach to any number of scenarios with [`Attach a guardrail to a scenario`](#tag/Scenario-Guardrails/operation/AttachGuardrailToScenario). Editing the definition later propagates to every attached scenario from its next meeting.
- [Get a guardrail](https://docs.waterr.ai/api-reference/endpoint/get-guardrails-id.md): Fetch one guardrail, including the scenarios it is attached to.
- [Update a guardrail](https://docs.waterr.ai/api-reference/endpoint/patch-guardrails-id.md): Partial update. Changes apply to every attached scenario from its next meeting — meetings already in progress keep the prompt they started with.
- [Delete a guardrail](https://docs.waterr.ai/api-reference/endpoint/delete-guardrails-id.md): Permanently delete the guardrail and detach it from every scenario. Not reversible — use `active: false` to disable it instead.
- [Meeting Skills](https://docs.waterr.ai/api-reference/skills.md): Instruction packs the agent loads mid-call and drops when done — define once, attach to any scenario.
- [List skills](https://docs.waterr.ai/api-reference/endpoint/get-skills.md): Return every skill on your account, newest first.
- [Create a skill](https://docs.waterr.ai/api-reference/endpoint/post-skills.md): Register a skill on your account, then attach it to any number of scenarios with [`Attach a skill to a scenario`](#tag/Scenario-Meeting-Skills/operation/AttachSkillToScenario). Names in `gated_tool_names` must match tools you created via [`Create a tool`](#tag/Tools/operation/CreateTool); a name tha…
- [Get a skill](https://docs.waterr.ai/api-reference/endpoint/get-skills-id.md): Fetch one skill, including the scenarios it is attached to.
- [Update a skill](https://docs.waterr.ai/api-reference/endpoint/patch-skills-id.md): Partial update. Changes apply to every attached scenario from its next meeting — meetings already in progress keep the skill set they started with.
- [Delete a skill](https://docs.waterr.ai/api-reference/endpoint/delete-skills-id.md): Permanently delete the skill and detach it from every scenario. Not reversible — use `active: false` to disable it instead.
- [Prompting Guide](https://docs.waterr.ai/api-reference/prompting-guide.md): Write effective meeting scripts that produce consistent, realistic AI conversations.
- [Examples](https://docs.waterr.ai/api-reference/examples.md): Complete integration examples for common use cases.
- [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 a real-time video meeting — no SDK, no rewrite, your infra.
- [LangChain](https://docs.waterr.ai/api-reference/langchain.md): Put your LangChain/LangGraph agent on a real-time video call as the persona — and let it create scenarios, dispatch meetings, and act on the results.
- [MCP Server](https://docs.waterr.ai/api-reference/mcp.md): Connect WaterrAI to Claude, ChatGPT, Cursor and other MCP-aware clients so your agent can list scenarios, fetch meetings, and pull analyses on your behalf.
- [Webhooks](https://docs.waterr.ai/api-reference/webhooks.md): Per-account, signed, retried webhooks. Configure once, receive every event that fires on your account, verify with a single shared secret.
- [Claude Code Skill](https://docs.waterr.ai/skills/claude-code.md): Install the WaterrAI skill into Claude Code with one command so your agent knows the API, the resource model, and scopes every build before writing code.
- [Codex Skill](https://docs.waterr.ai/skills/codex.md): Drop the WaterrAI agent instructions into your Codex project so it knows the API, the resource model, and scopes every build before writing code.

## OpenAPI Specs

- [openapi](/agent-mailbox/openapi.yaml)
- [openapi](/openapi.yaml)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.