Start Copilot Studio Conversation Node

S

Data/Microsoft/Copilot Studio

Open a conversation with a published Copilot Studio agent and return its ID, plus the agent's greeting when enabled (e.g. to show a welcome message when a chat opens).

data_microsoft_copilot_studio_start_conversationdataLong running

Inputs5

Outputs13

Security exposure8/10

Packagedata

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

SecurityAttack surface and exposure impact.

8/10High

PrivacyPotential sensitivity of processed data.

6/10Medium

PerformanceRuntime or resource pressure.

6/10Medium

GovernancePolicy, audit, or compliance impact.

8/10High

ReliabilityOperational stability considerations.

7/10High

CostExternal or compute cost impact.

5/10Medium

Input Pins

5

Input

Execution

exec_in

Trigger

Provider

Struct

provider

Copilot Studio provider with a delegated Power Platform token

SchemaCopilotStudioProviderCopilotStudioProviderCopilotStudioProvider2 fields

provider_idstringrequired

access_tokenstringrequired

Schema enforced

Agent

Struct

agent

Copilot Studio agent reference (from the Copilot Studio Agent node)

SchemaCopilotStudioAgentCopilotStudioAgentCopilotStudioAgent3 fields

conversations_urlstringrequired

`https://{environment host}/copilotstudio/…/bots/{schema name}/conversations`, without query.

environment_hoststringrequired

schema_namestringrequired

Schema enforced

Locale

String

locale

Language of the conversation, e.g. en-US or de-DE

Default en-US

Run Greeting

Boolean

run_greeting

Run the agent's Conversation Start topic and return its greeting

Default true

Output Pins

13

On Stream

Execution

on_stream

Fires for every streamed text or progress chunk

Chunk

Struct

chunk

Streamed chunk: answer text as content, progress updates as reasoning

SchemaResponseChunkResponseChunkResponseChunk8 fields

idstringrequired

choicesArray<ResponseChunkChoice>required

itemsResponseChunkChoicearray item

indexinteger:int32required

format int32

deltaanyOf (2)

variant 1Deltavariant

variant 2nullvariant

finish_reasonstring | null

logprobsanyOf (2)

variant 1LogProbsvariant

variant 2nullvariant

createdinteger | null

format uint64min 0

modelstring | null

service_tierstring | null

system_fingerprintstring | null

usageanyOf (2)

variant 1Usagevariant

completion_tokensinteger:uint32required

format uint32min 0

prompt_tokensinteger:uint32required

format uint32min 0

total_tokensinteger:uint32required

format uint32min 0

costnumber | null

format double

prompt_tokens_detailsanyOf (2)

variant 1PromptTokenDetailsvariant

variant 2nullvariant

+2 more fields

variant 2nullvariant

x_prefill_progressnumber | null

format float

Schema enforced

Done

Execution

done

The agent finished its turn

Error

Execution

error

The call failed

Result

Struct

result

The agent's reply with citations as annotations

SchemaResponseResponseResponse8 fields

idstring | null

choicesArray<Choice>required

itemsChoicearray item

indexinteger:int32required

format int32

finish_reasonstringrequired

messageResponseMessagerequired

rolestringrequired

contentstring | null

content_partsArray<Content>

Ordered structured content returned by Rig when the assistant response contains media. Text-only responses continue to use `content` alone for OpenAI compatibility.

refusalstring | null

annotationsarray | null

+3 more fields

logprobsanyOf (2)

variant 1LogProbsvariant

variant 2nullvariant

createdinteger | null

format uint64min 0

modelstring | null

service_tierstring | null

system_fingerprintstring | null

objectstring | null

usageUsagerequired

completion_tokensinteger:uint32required

format uint32min 0

prompt_tokensinteger:uint32required

format uint32min 0

total_tokensinteger:uint32required

format uint32min 0

costnumber | null

format double

prompt_tokens_detailsanyOf (2)

variant 1PromptTokenDetailsvariant

cached_tokensinteger | null

format uint32min 0

audio_tokensinteger | null

format uint32min 0

variant 2nullvariant

+2 more fields

Schema enforced

Conversation ID

String

new_conversation_id

Pass this into the next call to continue the conversation

Suggested Actions

String Array

suggested_actions

Quick replies the agent offered; send one back as the next message

Cards

Struct Array

cards

Adaptive Cards and other attachments the agent sent

SchemaCopilotStudioAttachmentCopilotStudioAttachmentCopilotStudioAttachment4 fields

content_typestringrequired

namestring | null

content_urlstring | null

contentvalue

default null

Attachments

Struct Array

attachments

Citations from generative answers, as chat attachments

SchemaAttachmentAttachmentAttachment2 fields

variant 1stringvariant

variant 2ComplexAttachmentvariant

urlstringrequired

preview_textstring | null

thumbnail_urlstring | null

namestring | null

sizeinteger | null

format uint64min 0

+3 more fields

Expecting Input

Boolean

expecting_input

The agent asked a question and waits for the user's answer

Conversation Ended

Boolean

conversation_ended

The agent ended the conversation; start a new one for the next message

Activities

Struct Array

activities

Every raw Bot Framework activity received in this call

SchemaBotActivityBotActivityBotActivity4 fields

typestring

default ""

idstring | null

namestring | null

textstring | null

Error Message

String

error_message

Why the call failed

Node Info

Internal name

data_microsoft_copilot_studio_start_conversation

Category

Data/Microsoft/Copilot Studio