How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Amigo conversations API

The conversations API from Amigo — 6 operation(s) for conversations.

Amigo conversations API is one of 72 APIs that Amigo publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Conversations. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.

This API exposes 7 operations across 6 paths, and defines 42 schemas. It is described by OpenAPI 3.2.0, at version 0.1.0.

Requests are made against 5 base URLs: https://api.amigo.ai, https://internal-api.amigo.ai, https://api-eu-central-1.amigo.ai, https://api-ap-southeast-2.amigo.ai, https://api-ca-central-1.amigo.ai.

7 operations 6 paths 42 schemas 1 DELETE1 GET5 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.1.0
Base URL
https://api.amigo.ai
Authentication
HTTP Bearer, API Key, HTTP Basic
Resource Areas
1

Authentication & Security 3

Amigo conversations API declares 3 security schemes for authenticating requests. It accepts HTTP bearer tokens (JWT) (Bearer-Authorization). An API key is passed in the header as X-ORG-ID (Bearer-Authorization-Organization). It accepts HTTP basic authentication (Basic). By default, every request must be authenticated.

  • Bearer-Authorization — Amigo issued JWT token that identifies an user. It's issued either after logging in through the frontend, or manually through the [SignInWithAPIKey](sign-in-wi…
  • Bearer-Authorization-Organization — An optional organization identifier that indicates from which organization the token is issued. This is used in rare cases where the user to authenticate is ma…
  • Basic — The username should be set to {orgid}{userid}, and the password should be the Amigo issued JWT token that identifies the user.

Paths & Operations 7

Across 6 paths, the API surfaces 7 operations — 1 DELETE, 1 GET, 5 POST. Each is listed below with its method, path, parameters, and response codes.

conversations 7
POST
/v1/{workspace_id}/conversations
Create or start a conversation (web inbound, or outbound on a channel)
create_conversation_v1__workspace_id__conversations_post 1 param body → 201422
POST
/v1/{workspace_id}/conversations/{conversation_id}/channel
Switch a conversation to another channel
switch_conversation_channel_v1__workspace_id__conversations__conversation_id__channel_post 2 params body → 200422
GET
/v1/{workspace_id}/conversations/{conversation_id}
Get conversation detail (voice or text)
get_conversation_v1__workspace_id__conversations__conversation_id__get 3 params → 200422
DELETE
/v1/{workspace_id}/conversations/{conversation_id}
Close a conversation
close_conversation_v1__workspace_id__conversations__conversation_id__delete 2 params → 204422
POST
/v1/{workspace_id}/conversations/{conversation_id}/turns
Send a message and get the agent's response
create_turn_v1__workspace_id__conversations__conversation_id__turns_post 4 params body → 200422
POST
/v1/{workspace_id}/conversations/{conversation_id}/turns/stream
Send a message and receive a streamed agent response
create_turn_stream_v1__workspace_id__conversations__conversation_id__turns_stream_post 3 params body → 200404409422503
POST
/v1/{workspace_id}/conversations/{conversation_id}/approval
Approve or reject a parked write in your own conversation (external-user self-approval)
decide_conversation_approval_v1__workspace_id__conversations__conversation_id__approval_post 2 params body → 204403404503422

Schemas 42

The contract defines 42 schemas that model the data the API accepts and returns. The most detailed are ConversationDetail (23 properties), VoiceDetail (22 properties), ActionState-Output (16 properties), DataCollectionState-Output (14 properties). Each schema is shown below with its type and property counts.

ExitCondition
object
3 properties 2 required
ConversationToolCallDetail
object
7 properties 2 required
TurnToolCallStartedEvent
object
4 properties 3 required
DecisionState-Output
object
Passthrough routing state — Agent picks an exit condition, no user interaction.
10 properties 4 required
TurnConversationSnapshot
object
5 properties 3 required
ConversationTurnAvailableAction
object
1 property 1 required
ConversationTurn
object
12 properties 2 required
PhoneE164
string
TurnThinkingEvent
object
3 properties 2 required
TurnTokenEvent
object
2 properties 1 required
ProgressHint
object
How the agent narrates waiting on a tool. deterministic=true: scripted — phrases play verbatim in order. deterministic=false: engine picks — phrases are hints.…
8 properties
ChannelKind
string
HSM execution channel type. Determines how the HSM engine communicates with end users. Each kind maps to one or more providers.
NameString
string
BackgroundString
string
SwitchChannelRequest
object
6 properties 2 required
TurnPolicy
object
Voice pipeline parameters declared per HSM state. Lives on ActionState/DecisionState alongside guardrails, waitfor, and channeloverrides. The HSM state IS the…
10 properties
TurnToolCallCompletedEvent
object
6 properties 4 required
CollectionField
object
A single field to collect during a data collection state.
8 properties 3 required
Guardrail
object
Typed safety rule enforced per-state (not just global freetext guidelines).
3 properties 2 required
ConversationTurnStateTransition
object
2 properties 2 required
VoiceDetail
object
22 properties
CreateConversationRequest
object
7 properties 1 required
HTTPValidationError
object
1 property
ValidationError
object
5 properties 3 required
TurnErrorEvent
object
Terminal error frame on the turn stream. Carries a stable code so SDK consumers can branch deterministically without parsing free-form message text. retryable…
5 properties 1 required
ConversationDetail
object
23 properties 6 required
ToolCallSpec
object
A tool call that the agent can make in a state.
12 properties 1 required
TurnMessageEvent
object
3 properties 2 required
TurnDoneEvent
object
8 properties 3 required
PreloadSpec
object
A tool call executed deterministically by the engine on state entry. Unlike LLM-driven tool calls, preloads run before any LLM turn — the results appear in the…
2 properties 1 required
DataCollectionState-Output
object
Structured voice/text data collection with field tracking. The engine presents fields conversationally, tracks completion, and optionally falls back to a Surfa…
14 properties 5 required
TurnRequest
object
9 properties
TurnResponse
object
6 properties 4 required
ConversationApprovalRequest
object
An external user's decision on a parked, approval-gated write in their own conversation.
2 properties 1 required
ActionState-Output
object
User-facing engagement state with actions and exit conditions.
16 properties 8 required
FailureClass
string
Why a tool result is a failure — produced by the executor at RUN time. Unlike ResultDelivery (a fixed config-time axis), this is a runtime classification the e…
Action
object
A single action the agent can take within a state.
2 properties 1 required
ChannelOverride
object
Per-channel behavior override for a state.
3 properties
TurnStreamEvent
AnnotationState
object
Injects a hardcoded inner thought (no LLM call).
4 properties 4 required
ContentPartPayload
object
HTTP/WebSocket shape for a modality-neutral conversation content part.
6 properties
ContextGraphState-Output

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

amigo-conversations-api-openapi.yml Raw ↑

Other APIs Amigo publishes across the network.

Amigo Account API
Amigo Admin API
Amigo Agent Definitions API
Amigo Agent Runs API
Amigo Agents API
Amigo Analytics API
Amigo API Keys API
Amigo Audit API
Amigo Auth API
Amigo Billing API
Amigo Calls API
Amigo Command Center API
Where this information came from

This is an independent, third-party profile of Amigo conversations 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.