Agentic Flows¶
Use an API key or REST OAuth access token. Scopes and your current workspace permissions apply together. All examples are illustrative.
Read Flow configuration catalog¶
Scope: flows:read
Response 200
Success.
| Header | Type | Description |
|---|---|---|
Cache-Control |
string |
The response must not be cached. Example: no-store |
application/json
| Field | Type | Description |
|---|---|---|
models |
List of object |
Models available with the current user's permissions. |
routingModes |
List of string |
Available routing methods. Values: LLM, DECISION |
promptVariables |
List of object |
Prompt variables supported by this configuration. |
models — fields
| Field | Type | Description |
|---|---|---|
value |
string |
Exact catalog value to send in API requests.Show all 19 allowed values
|
fixedTemperature |
number (double) |
Temperature required by this model, if fixed. |
maxOutputTokens |
integer (int32) |
Maximum output-token budget supported by this model. |
promptVariables — fields
| Field | Type | Description |
|---|---|---|
key |
string |
Name of the variable or parameter. |
label |
string |
Display label for this value or variable. |
helperText |
string |
Explanation of how to use the prompt variable. |
category |
string |
Category used to group prompt variables. Values: AGENT, ROUTING |
Error responses
| Status | Meaning |
|---|---|
400 |
Invalid input, unsupported selection or time range. |
401 |
Missing, expired or invalid credential. The body may be empty. |
403 |
Required scope or current user permission missing. The body may be empty. |
429 |
Shared workspace budget exceeded. Honor Retry-After; do not blindly replay uncertain writes. |
503 |
Temporarily unavailable. Check uncertain writes before retrying. |
Error body
| Field | Type | Description |
|---|---|---|
status |
integer |
HTTP status code. |
error |
string |
Description of the error. |
details |
any |
Additional error details, when available. Rules: null allowed |
code |
string |
Machine-readable error code. |
params |
object |
Additional values associated with the error code. |
fieldErrors |
object |
Validation errors grouped by input field. |
For 429 or 503, honor the Retry-After header (seconds). Check uncertain writes before retrying.
Create Agentic Flow¶
Scope: flows:write
Saves configuration directly; no call, tool test or message delivery is executed.
Request body · application/json
| Field | Type | Required | Description |
|---|---|---|---|
title |
string |
Yes | Display name of the resource. Rules: up to 255 characters Example: "Demo" |
description |
string |
No | Description of this resource's purpose. Rules: up to 255 characters |
persona |
string |
No | Shared personality and speaking style for Agents in this Flow. Rules: up to 100000 characters |
routingPrompt |
string |
No | Instructions for LLM routing. Use variables from the Flow catalog. Rules: up to 100000 characters |
model |
string |
Yes | Routing model from the Flow catalog. Check its temperature and output limits.Show all 19 allowed values
|
conversationHistoryLimit |
integer (int32) |
Yes | Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
temperature |
number (double) |
Yes | Routing-response variation. Respect any fixed temperature in the Flow catalog. Rules: 0–2Example: 0.3 |
maxTokens |
integer (int32) |
Yes | Maximum output-token budget. Also respect the selected model's limit in the catalog. Rules: 10–25000Example: 1000 |
intentAgentMapping |
object |
Yes | Map intent names to Agent IDs in this workspace. Include DEFAULT as the fallback. Rules: at least 1 key Example: {"DEFAULT": "00000000-0000-0000-0000-000000000001"}Each value: string (uuid) |
routingMode |
string |
Yes | Routing method selected from the Flow catalog. Values: LLM, DECISION |
decisionRouting |
object |
No | Decision-routing settings. Omitting this field or sending null on update keeps the existing draft. |
decisionRouting — fields
| Field | Type | Required | Description |
|---|---|---|---|
instructions |
string |
No | Instructions for choosing a routing intent. Rules: up to 20000 characters |
intentDescriptions |
object |
No | Describe when each active intent applies, including DEFAULT. Each value: string |
conversationHistoryLimit |
integer (int32) |
Yes | Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
{
"title": "Demo",
"description": "string",
"persona": "string",
"routingPrompt": "string",
"model": "GPT_4_1_MINI",
"conversationHistoryLimit": 10,
"temperature": 0.3,
"maxTokens": 1000,
"intentAgentMapping": {
"DEFAULT": "00000000-0000-0000-0000-000000000001"
},
"routingMode": "LLM",
"decisionRouting": {
"instructions": "string",
"intentDescriptions": {},
"conversationHistoryLimit": 10
}
}
Response 201
Created.
| Header | Type | Description |
|---|---|---|
Cache-Control |
string |
The response must not be cached. Example: no-store |
Location |
string |
Path of the created resource. |
ETag |
string |
Current revision. Send unchanged, including quotes, as If-Match when required. Example: "revision-from-get" |
application/json
| Field | Type | Description |
|---|---|---|
id |
string (uuid) |
Resource ID in your workspace. |
revision |
string |
Current resource revision. Use the response ETag for If-Match when updating. |
configuration |
object |
Settings for this resource. Send the complete editable configuration when updating. |
configuration — fields
| Field | Type | Description |
|---|---|---|
title |
string |
Display name of the resource. Rules: up to 255 characters Example: "Demo" |
description |
string |
Description of this resource's purpose. Rules: up to 255 characters |
persona |
string |
Shared personality and speaking style for Agents in this Flow. Rules: up to 100000 characters |
routingPrompt |
string |
Instructions for LLM routing. Use variables from the Flow catalog. Rules: up to 100000 characters |
model |
string |
Routing model from the Flow catalog. Check its temperature and output limits.Show all 19 allowed values
|
conversationHistoryLimit |
integer (int32) |
Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
temperature |
number (double) |
Routing-response variation. Respect any fixed temperature in the Flow catalog. Rules: 0–2Example: 0.3 |
maxTokens |
integer (int32) |
Maximum output-token budget. Also respect the selected model's limit in the catalog. Rules: 10–25000Example: 1000 |
intentAgentMapping |
object |
Map intent names to Agent IDs in this workspace. Include DEFAULT as the fallback. Rules: at least 1 key Example: {"DEFAULT": "00000000-0000-0000-0000-000000000001"}Each value: string (uuid) |
routingMode |
string |
Routing method selected from the Flow catalog. Values: LLM, DECISION |
decisionRouting |
object |
Decision-routing settings. Omitting this field or sending null on update keeps the existing draft. |
decisionRouting — fields
| Field | Type | Description |
|---|---|---|
instructions |
string |
Instructions for choosing a routing intent. Rules: up to 20000 characters |
intentDescriptions |
object |
Describe when each active intent applies, including DEFAULT. Each value: string |
conversationHistoryLimit |
integer (int32) |
Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
{
"id": "00000000-0000-0000-0000-000000000001",
"revision": "revision-from-get",
"configuration": {
"title": "Demo",
"description": "string",
"persona": "string",
"routingPrompt": "string",
"model": "GPT_4_1_MINI",
"conversationHistoryLimit": 10,
"temperature": 0.3,
"maxTokens": 1000,
"intentAgentMapping": {
"DEFAULT": "00000000-0000-0000-0000-000000000001"
},
"routingMode": "LLM",
"decisionRouting": {
"instructions": "string",
"intentDescriptions": {},
"conversationHistoryLimit": 10
}
}
}
Error responses
| Status | Meaning |
|---|---|
400 |
Invalid input, unsupported selection or time range. |
401 |
Missing, expired or invalid credential. The body may be empty. |
403 |
Required scope or current user permission missing. The body may be empty. |
409 |
Missing/stale revision or dependency/routing conflict. Read again before retrying. |
429 |
Shared workspace budget exceeded. Honor Retry-After; do not blindly replay uncertain writes. |
503 |
Temporarily unavailable. Check uncertain writes before retrying. |
Error body
| Field | Type | Description |
|---|---|---|
status |
integer |
HTTP status code. |
error |
string |
Description of the error. |
details |
any |
Additional error details, when available. Rules: null allowed |
code |
string |
Machine-readable error code. |
params |
object |
Additional values associated with the error code. |
fieldErrors |
object |
Validation errors grouped by input field. |
For 429 or 503, honor the Retry-After header (seconds). Check uncertain writes before retrying.
List Agentic Flows¶
Scope: flows:read
Parameters
| Name | Location | Type | Required | Description |
|---|---|---|---|---|
page |
Query | integer (int32) |
No | Page index, starting at 0. Rules: 0–100000Default: 0 |
size |
Query | integer (int32) |
No | Results per page. Rules: 1–100Default: 25 |
Response 200
Success.
| Header | Type | Description |
|---|---|---|
Cache-Control |
string |
The response must not be cached. Example: no-store |
application/json
| Field | Type | Description |
|---|---|---|
items |
List of object |
Results on this page. |
page |
integer (int32) |
Current page index, starting at 0. |
size |
integer (int32) |
Number of results requested per page. |
totalElements |
integer (int64) |
Total number of matching results. |
totalPages |
integer (int32) |
Total number of result pages. |
items — fields
| Field | Type | Description |
|---|---|---|
id |
string (uuid) |
Resource ID in your workspace. |
revision |
string |
Current resource revision. Use the response ETag for If-Match when updating. |
title |
string |
Display name of the resource. |
description |
string |
Description of this resource's purpose. |
routingMode |
string |
Routing method selected from the Flow catalog. Values: LLM, DECISION |
Error responses
| Status | Meaning |
|---|---|
400 |
Invalid input, unsupported selection or time range. |
401 |
Missing, expired or invalid credential. The body may be empty. |
403 |
Required scope or current user permission missing. The body may be empty. |
429 |
Shared workspace budget exceeded. Honor Retry-After; do not blindly replay uncertain writes. |
503 |
Temporarily unavailable. Check uncertain writes before retrying. |
Error body
| Field | Type | Description |
|---|---|---|
status |
integer |
HTTP status code. |
error |
string |
Description of the error. |
details |
any |
Additional error details, when available. Rules: null allowed |
code |
string |
Machine-readable error code. |
params |
object |
Additional values associated with the error code. |
fieldErrors |
object |
Validation errors grouped by input field. |
For 429 or 503, honor the Retry-After header (seconds). Check uncertain writes before retrying.
Delete Agentic Flow¶
Scope: flows:write
Read the resource first. Send its current ETag, including quotes, in If-Match.
Parameters
| Name | Location | Type | Required | Description |
|---|---|---|---|---|
id |
Path | string (uuid) |
Yes | Resource identifier in the bound workspace. |
If-Match |
Header | string |
Yes | ETag from the preceding read, including quotes. Example: "revision-from-get" |
Response 204
Deleted; no response body.
| Header | Type | Description |
|---|---|---|
Cache-Control |
string |
The response must not be cached. Example: no-store |
Error responses
| Status | Meaning |
|---|---|
400 |
Invalid input, unsupported selection or time range. |
401 |
Missing, expired or invalid credential. The body may be empty. |
403 |
Required scope or current user permission missing. The body may be empty. |
404 |
Resource is unavailable in the bound workspace. |
409 |
Missing/stale revision or dependency/routing conflict. Read again before retrying. |
429 |
Shared workspace budget exceeded. Honor Retry-After; do not blindly replay uncertain writes. |
503 |
Temporarily unavailable. Check uncertain writes before retrying. |
Error body
| Field | Type | Description |
|---|---|---|
status |
integer |
HTTP status code. |
error |
string |
Description of the error. |
details |
any |
Additional error details, when available. Rules: null allowed |
code |
string |
Machine-readable error code. |
params |
object |
Additional values associated with the error code. |
fieldErrors |
object |
Validation errors grouped by input field. |
For 429 or 503, honor the Retry-After header (seconds). Check uncertain writes before retrying.
Read Agentic Flow¶
Scope: flows:read
Parameters
| Name | Location | Type | Required | Description |
|---|---|---|---|---|
id |
Path | string (uuid) |
Yes | Resource identifier in the bound workspace. |
Response 200
Success.
| Header | Type | Description |
|---|---|---|
Cache-Control |
string |
The response must not be cached. Example: no-store |
ETag |
string |
Current revision. Send unchanged, including quotes, as If-Match when required. Example: "revision-from-get" |
application/json
| Field | Type | Description |
|---|---|---|
id |
string (uuid) |
Resource ID in your workspace. |
revision |
string |
Current resource revision. Use the response ETag for If-Match when updating. |
configuration |
object |
Settings for this resource. Send the complete editable configuration when updating. |
configuration — fields
| Field | Type | Description |
|---|---|---|
title |
string |
Display name of the resource. Rules: up to 255 characters Example: "Demo" |
description |
string |
Description of this resource's purpose. Rules: up to 255 characters |
persona |
string |
Shared personality and speaking style for Agents in this Flow. Rules: up to 100000 characters |
routingPrompt |
string |
Instructions for LLM routing. Use variables from the Flow catalog. Rules: up to 100000 characters |
model |
string |
Routing model from the Flow catalog. Check its temperature and output limits.Show all 19 allowed values
|
conversationHistoryLimit |
integer (int32) |
Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
temperature |
number (double) |
Routing-response variation. Respect any fixed temperature in the Flow catalog. Rules: 0–2Example: 0.3 |
maxTokens |
integer (int32) |
Maximum output-token budget. Also respect the selected model's limit in the catalog. Rules: 10–25000Example: 1000 |
intentAgentMapping |
object |
Map intent names to Agent IDs in this workspace. Include DEFAULT as the fallback. Rules: at least 1 key Example: {"DEFAULT": "00000000-0000-0000-0000-000000000001"}Each value: string (uuid) |
routingMode |
string |
Routing method selected from the Flow catalog. Values: LLM, DECISION |
decisionRouting |
object |
Decision-routing settings. Omitting this field or sending null on update keeps the existing draft. |
decisionRouting — fields
| Field | Type | Description |
|---|---|---|
instructions |
string |
Instructions for choosing a routing intent. Rules: up to 20000 characters |
intentDescriptions |
object |
Describe when each active intent applies, including DEFAULT. Each value: string |
conversationHistoryLimit |
integer (int32) |
Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
{
"id": "00000000-0000-0000-0000-000000000001",
"revision": "revision-from-get",
"configuration": {
"title": "Demo",
"description": "string",
"persona": "string",
"routingPrompt": "string",
"model": "GPT_4_1_MINI",
"conversationHistoryLimit": 10,
"temperature": 0.3,
"maxTokens": 1000,
"intentAgentMapping": {
"DEFAULT": "00000000-0000-0000-0000-000000000001"
},
"routingMode": "LLM",
"decisionRouting": {
"instructions": "string",
"intentDescriptions": {},
"conversationHistoryLimit": 10
}
}
}
Error responses
| Status | Meaning |
|---|---|
400 |
Invalid input, unsupported selection or time range. |
401 |
Missing, expired or invalid credential. The body may be empty. |
403 |
Required scope or current user permission missing. The body may be empty. |
404 |
Resource is unavailable in the bound workspace. |
429 |
Shared workspace budget exceeded. Honor Retry-After; do not blindly replay uncertain writes. |
503 |
Temporarily unavailable. Check uncertain writes before retrying. |
Error body
| Field | Type | Description |
|---|---|---|
status |
integer |
HTTP status code. |
error |
string |
Description of the error. |
details |
any |
Additional error details, when available. Rules: null allowed |
code |
string |
Machine-readable error code. |
params |
object |
Additional values associated with the error code. |
fieldErrors |
object |
Validation errors grouped by input field. |
For 429 or 503, honor the Retry-After header (seconds). Check uncertain writes before retrying.
Update Agentic Flow¶
Scope: flows:write
Saves configuration directly; no call, tool test or message delivery is executed. Read the resource first. Send its current ETag, including quotes, in If-Match. Send the full editable configuration. Omitted settings can be reset.
Parameters
| Name | Location | Type | Required | Description |
|---|---|---|---|---|
id |
Path | string (uuid) |
Yes | Resource identifier in the bound workspace. |
If-Match |
Header | string |
Yes | ETag from the preceding read, including quotes. Example: "revision-from-get" |
Request body · application/json
| Field | Type | Required | Description |
|---|---|---|---|
title |
string |
Yes | Display name of the resource. Rules: up to 255 characters Example: "Demo" |
description |
string |
No | Description of this resource's purpose. Rules: up to 255 characters |
persona |
string |
No | Shared personality and speaking style for Agents in this Flow. Rules: up to 100000 characters |
routingPrompt |
string |
No | Instructions for LLM routing. Use variables from the Flow catalog. Rules: up to 100000 characters |
model |
string |
Yes | Routing model from the Flow catalog. Check its temperature and output limits.Show all 19 allowed values
|
conversationHistoryLimit |
integer (int32) |
Yes | Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
temperature |
number (double) |
Yes | Routing-response variation. Respect any fixed temperature in the Flow catalog. Rules: 0–2Example: 0.3 |
maxTokens |
integer (int32) |
Yes | Maximum output-token budget. Also respect the selected model's limit in the catalog. Rules: 10–25000Example: 1000 |
intentAgentMapping |
object |
Yes | Map intent names to Agent IDs in this workspace. Include DEFAULT as the fallback. Rules: at least 1 key Example: {"DEFAULT": "00000000-0000-0000-0000-000000000001"}Each value: string (uuid) |
routingMode |
string |
Yes | Routing method selected from the Flow catalog. Values: LLM, DECISION |
decisionRouting |
object |
No | Decision-routing settings. Omitting this field or sending null on update keeps the existing draft. |
decisionRouting — fields
| Field | Type | Required | Description |
|---|---|---|---|
instructions |
string |
No | Instructions for choosing a routing intent. Rules: up to 20000 characters |
intentDescriptions |
object |
No | Describe when each active intent applies, including DEFAULT. Each value: string |
conversationHistoryLimit |
integer (int32) |
Yes | Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
{
"title": "Demo",
"description": "string",
"persona": "string",
"routingPrompt": "string",
"model": "GPT_4_1_MINI",
"conversationHistoryLimit": 10,
"temperature": 0.3,
"maxTokens": 1000,
"intentAgentMapping": {
"DEFAULT": "00000000-0000-0000-0000-000000000001"
},
"routingMode": "LLM",
"decisionRouting": {
"instructions": "string",
"intentDescriptions": {},
"conversationHistoryLimit": 10
}
}
Response 200
Success.
| Header | Type | Description |
|---|---|---|
Cache-Control |
string |
The response must not be cached. Example: no-store |
ETag |
string |
Current revision. Send unchanged, including quotes, as If-Match when required. Example: "revision-from-get" |
application/json
| Field | Type | Description |
|---|---|---|
id |
string (uuid) |
Resource ID in your workspace. |
revision |
string |
Current resource revision. Use the response ETag for If-Match when updating. |
configuration |
object |
Settings for this resource. Send the complete editable configuration when updating. |
configuration — fields
| Field | Type | Description |
|---|---|---|
title |
string |
Display name of the resource. Rules: up to 255 characters Example: "Demo" |
description |
string |
Description of this resource's purpose. Rules: up to 255 characters |
persona |
string |
Shared personality and speaking style for Agents in this Flow. Rules: up to 100000 characters |
routingPrompt |
string |
Instructions for LLM routing. Use variables from the Flow catalog. Rules: up to 100000 characters |
model |
string |
Routing model from the Flow catalog. Check its temperature and output limits.Show all 19 allowed values
|
conversationHistoryLimit |
integer (int32) |
Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
temperature |
number (double) |
Routing-response variation. Respect any fixed temperature in the Flow catalog. Rules: 0–2Example: 0.3 |
maxTokens |
integer (int32) |
Maximum output-token budget. Also respect the selected model's limit in the catalog. Rules: 10–25000Example: 1000 |
intentAgentMapping |
object |
Map intent names to Agent IDs in this workspace. Include DEFAULT as the fallback. Rules: at least 1 key Example: {"DEFAULT": "00000000-0000-0000-0000-000000000001"}Each value: string (uuid) |
routingMode |
string |
Routing method selected from the Flow catalog. Values: LLM, DECISION |
decisionRouting |
object |
Decision-routing settings. Omitting this field or sending null on update keeps the existing draft. |
decisionRouting — fields
| Field | Type | Description |
|---|---|---|
instructions |
string |
Instructions for choosing a routing intent. Rules: up to 20000 characters |
intentDescriptions |
object |
Describe when each active intent applies, including DEFAULT. Each value: string |
conversationHistoryLimit |
integer (int32) |
Maximum number of conversation-history entries supplied to the model. Rules: 0–100Example: 10 |
{
"id": "00000000-0000-0000-0000-000000000001",
"revision": "revision-from-get",
"configuration": {
"title": "Demo",
"description": "string",
"persona": "string",
"routingPrompt": "string",
"model": "GPT_4_1_MINI",
"conversationHistoryLimit": 10,
"temperature": 0.3,
"maxTokens": 1000,
"intentAgentMapping": {
"DEFAULT": "00000000-0000-0000-0000-000000000001"
},
"routingMode": "LLM",
"decisionRouting": {
"instructions": "string",
"intentDescriptions": {},
"conversationHistoryLimit": 10
}
}
}
Error responses
| Status | Meaning |
|---|---|
400 |
Invalid input, unsupported selection or time range. |
401 |
Missing, expired or invalid credential. The body may be empty. |
403 |
Required scope or current user permission missing. The body may be empty. |
404 |
Resource is unavailable in the bound workspace. |
409 |
Missing/stale revision or dependency/routing conflict. Read again before retrying. |
429 |
Shared workspace budget exceeded. Honor Retry-After; do not blindly replay uncertain writes. |
503 |
Temporarily unavailable. Check uncertain writes before retrying. |
Error body
| Field | Type | Description |
|---|---|---|
status |
integer |
HTTP status code. |
error |
string |
Description of the error. |
details |
any |
Additional error details, when available. Rules: null allowed |
code |
string |
Machine-readable error code. |
params |
object |
Additional values associated with the error code. |
fieldErrors |
object |
Validation errors grouped by input field. |
For 429 or 503, honor the Retry-After header (seconds). Check uncertain writes before retrying.