WaterrAI API API is one of 2 APIs that waterr-ai publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
This API exposes 6 JSON Schema definitions.
The published artifact set on APIs.io includes an OpenAPI specification and 6 JSON Schemas.
This API exposes
69 operations
across 42 paths,
organized into 15 resource areas,
and defines 17 schemas.
It is described by OpenAPI 3.0.0, at version 1.0.0.
Requests are made against a single base URL, https://api.waterr.ai/v1.
69 operations42 paths17 schemas11 DELETE31 GET5 PATCH16 POST6 PUT
Metadata
The identity and technical contract details declared by the specification.
WaterrAI API API declares
1 security scheme
for authenticating requests.
It accepts HTTP bearer tokens (wai_...) (apiKeyAuth).
By default, every request must be authenticated.
apiKeyAuth — API key from waterr.ai/settings?tab=api-keys. Send as Authorization: Bearer wai .
Paths & Operations 69
Across 42 paths, the API surfaces 69 operations — 11 DELETE, 31 GET, 5 PATCH, 16 POST, 6 PUT. They span 15 resource areas, including Analyses, Goals, Meetings, Avatars, Personas, Recordings, Scenarios, Transcripts, and 7 more. Each is listed below with its method, path, parameters, and response codes.
Verify the signed token a screen app (presented page) received for the meeting it was opened in.
POST
/stage-tokens/introspect
Introspect a stage token
IntrospectStageTokenbody→ 200400401
Guardrails 5
Account-scoped named prompt fragments appended to a scenario's system prompt.
GET
/guardrails
List guardrails
ListGuardrails→ 200401500
POST
/guardrails
Create a guardrail
CreateGuardrailbody→ 201400401409
GET
/guardrails/{id}
Get a guardrail
GetGuardrail1 param→ 200401404
PATCH
/guardrails/{id}
Update a guardrail
UpdateGuardrail1 parambody→ 200400401404409
DELETE
/guardrails/{id}
Delete a guardrail
DeleteGuardrail1 param→ 204401404
Meeting Skills 5
Account-scoped invokable instruction packs the agent loads mid-meeting.
GET
/skills
List skills
ListSkills→ 200401500
POST
/skills
Create a skill
CreateSkillbody→ 201400401409
GET
/skills/{id}
Get a skill
GetSkill1 param→ 200401404
PATCH
/skills/{id}
Update a skill
UpdateSkill1 parambody→ 200400401404409
DELETE
/skills/{id}
Delete a skill
DeleteSkill1 param→ 204401404
Memories 8
Facts your agents remember, in containers named by usermemorytag and shared across agents.
GET
/memories
List the memories under a tag
ListMemories2 params→ 200400401
POST
/memories
Add memories
ImportMemoriesbody→ 201400401404
GET
/memories/tags
List memory containers
ListMemoryContainers1 param→ 200401
GET
/memories/tags/{tag}
Get a memory container
GetMemoryContainer1 param→ 200401404
DELETE
/memories/tags/{tag}
Delete a memory container
DeleteMemoryContainer1 param→ 204401404
GET
/memories/{id}
Get a memory
GetMemory1 param→ 200401404
PATCH
/memories/{id}
Update a memory
UpdateMemory1 parambody→ 200400401404409
DELETE
/memories/{id}
Delete a memory
DeleteMemory1 param→ 204401404
Schemas 17
The contract defines 17 schemas that model the data the API accepts and returns. The most detailed are MeetingControls (18 properties), Avatar (17 properties), CustomFunction (16 properties), Analysis (14 properties). Each schema is shown below with its type and property counts.
GoalResult
object
7 properties
Analysis
object
14 properties
User
object
6 properties
AuthResponse
object
3 properties
ErrorResponse
object
3 properties
MeetingControls
object
18 properties
Scenario
object
13 properties
Voice
object
7 properties
Avatar
object
A catalog avatar — the visual identity a persona presents in prejoin cards and meetings. Global curated avatars have ownermembershipid: null; avatars you gener…
17 properties
CustomFunction
object
A tool the LLM can call mid-meeting. Defined once on your account, attached to one or more scenarios.
16 properties8 required
ScenarioCustomFunctionAttachment
object
Links a tool to a scenario. The tool is advertised to the LLM only when active = true.
8 properties4 required
Guardrail
object
A named prompt fragment. Every guardrail attached to a scenario is appended to that scenario's system prompt as a bullet under a Guardrails heading, so the per…
8 properties4 required
ScenarioGuardrailAttachment
object
Links a guardrail to a scenario. The rule enters the system prompt only when active = true.
8 properties4 required
Skill
object
An invokable instruction pack. Only the one-line trigger sits in the agent's prompt each turn; the full instructions load when the agent invokes the skill mid-…
10 properties5 required
ScenarioSkillAttachment
object
Links a skill to a scenario. The trigger reaches the agent only when active = true.
8 properties4 required
Memory
object
One remembered fact, held in the container named by its usermemorytag. Every agent with memory on that runs a call under that tag is told it at the start of th…
9 properties
MemoryContainer
object
Every memory under one usermemorytag in your workspace.
7 properties
Specification
The full machine-readable OpenAPI contract behind this narrative.
Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.
Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.
MCP tools for apis
4 tools reach this content
search_api_evangelistSearch every content type across the network at once.
find_relatedThe shared-tag relevance graph — what else covers this.
get_tagEverything one tag labels, across all content types.
guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
A second provider on the same verified email joins the account you already have.
Your account
ⓘWhere this information came from
This is an independent, third-party profile of WaterrAI API API, published by
API Evangelist. We do not operate, host, resell, or
support these APIs, and we are not affiliated with or endorsed by the company unless stated above.
Everything here is built from publicly available information — the company's own site,
developer portal, documentation, public repositories, and the specifications it publishes for public use.
Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's
public API artifacts, scored against a published rubric. They are not certifications,
endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and
you do not need to justify the request. A removed company is recorded as unrated, never scored
zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy → On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.