AI Agent Subprocess
Processes user requests with an integrated, customizable toolbox and services for dynamic workflows.
Required inputs
| Key | Label | Type |
|---|---|---|
provider.anthropic.authentication.apiKey | Anthropic API key | secret |
provider.bedrock.region | Region | FEEL expression |
provider.bedrock.authentication.accessKey | Access key | secret |
provider.bedrock.authentication.secretKey | Secret key | secret |
provider.azureOpenAi.endpoint | Endpoint | FEEL expression |
provider.azureOpenAi.authentication.apiKey | API key | secret |
provider.azureOpenAi.authentication.clientId | Client ID | FEEL expression |
provider.azureOpenAi.authentication.clientSecret | Client secret | secret |
provider.azureOpenAi.authentication.tenantId | Tenant ID | FEEL expression |
provider.googleVertexAi.projectId | Project ID | FEEL expression |
provider.googleVertexAi.region | Region | FEEL expression |
provider.googleVertexAi.authentication.jsonKey | JSON key of the service account | FEEL expression |
provider.openai.authentication.apiKey | OpenAI API key | secret |
provider.openaiCompatible.endpoint | API endpoint | FEEL expression |
provider.anthropic.model.model | Model | FEEL expression |
provider.bedrock.model.model | Model | FEEL expression |
provider.azureOpenAi.model.deploymentName | Model deployment name | FEEL expression |
provider.googleVertexAi.model.model | Model | FEEL expression |
provider.openai.model.model | Model | FEEL expression |
provider.openaiCompatible.model.model | Model | FEEL expression |
data.systemPrompt.prompt | System prompt | FEEL expression |
data.userPrompt.prompt | User prompt | FEEL expression |
data.memory.storage.storeType | Implementation type | FEEL expression |
data.events.behavior | Event handling behavior | string |
Optional inputs
| Key | Label | Type |
|---|---|---|
provider.type | Provider | string |
provider.anthropic.endpoint | Endpoint | FEEL expression |
provider.bedrock.endpoint | Endpoint | FEEL expression |
provider.bedrock.authentication.type | Authentication | string |
provider.azureOpenAi.authentication.type | Authentication | string |
provider.azureOpenAi.authentication.authorityHost | Authority host | FEEL expression |
provider.googleVertexAi.authentication.type | Authentication | string |
provider.openai.authentication.organizationId | Organization ID | FEEL expression |
provider.openai.authentication.projectId | Project ID | FEEL expression |
provider.openaiCompatible.authentication.apiKey | API key | secret |
provider.openaiCompatible.headers | Headers | FEEL expression |
provider.anthropic.model.parameters.maxTokens | Maximum tokens | secret |
provider.anthropic.model.parameters.temperature | Temperature | FEEL expression |
provider.anthropic.model.parameters.topP | top P | FEEL expression |
provider.anthropic.model.parameters.topK | top K | FEEL expression |
provider.bedrock.model.parameters.maxTokens | Maximum tokens | secret |
provider.bedrock.model.parameters.temperature | Temperature | FEEL expression |
provider.bedrock.model.parameters.topP | top P | FEEL expression |
provider.azureOpenAi.model.parameters.maxTokens | Maximum tokens | secret |
provider.azureOpenAi.model.parameters.temperature | Temperature | FEEL expression |
provider.azureOpenAi.model.parameters.topP | top P | FEEL expression |
provider.googleVertexAi.model.parameters.maxOutputTokens | Maximum output tokens | secret |
provider.googleVertexAi.model.parameters.temperature | Temperature | FEEL expression |
provider.googleVertexAi.model.parameters.topP | top P | FEEL expression |
provider.googleVertexAi.model.parameters.topK | top K | FEEL expression |
provider.openai.model.parameters.maxCompletionTokens | Maximum completion tokens | secret |
provider.openai.model.parameters.temperature | Temperature | FEEL expression |
provider.openai.model.parameters.topP | top P | FEEL expression |
provider.openaiCompatible.model.parameters.maxCompletionTokens | Maximum completion tokens | secret |
provider.openaiCompatible.model.parameters.temperature | Temperature | FEEL expression |
provider.openaiCompatible.model.parameters.topP | top P | FEEL expression |
provider.openaiCompatible.model.parameters.customParameters | Custom parameters | FEEL expression |
data.userPrompt.documents | Documents | FEEL expression |
agentContext | Agent context | FEEL expression |
data.memory.storage.type | Memory storage type | string |
data.memory.storage.timeToLive | Document TTL | FEEL expression |
data.memory.storage.customProperties | Custom document properties | FEEL expression |
data.memory.storage.parameters | Parameters | FEEL expression |
data.memory.contextWindowSize | Context window size | string |
data.limits.maxModelCalls | Maximum model calls | string |
data.response.format.type | Response format | string |
data.response.format.parseJson | Parse text as JSON | string |
data.response.format.schema | Response JSON schema | FEEL expression |
data.response.format.schemaName | Response JSON schema name | FEEL expression |
data.response.includeAssistantMessage | Include assistant message | string |
data.response.includeAgentContext | Include agent context | string |
resultVariable | Result variable | string |
errorExpression | Error expression | FEEL expression |
retryCount | Retries | FEEL expression |
retryBackoff | Retry backoff | string |
Apply this connector with @bpmnkit/connectors
import { applyConnectorTemplate } from "@bpmnkit/connectors"
const result = applyConnectorTemplate("io.camunda.connectors.agenticai.aiagent.jobworker.v1", {
"provider.anthropic.authentication.apiKey": "<your anthropic api key>",
"provider.bedrock.region": "= ...",
"provider.bedrock.authentication.accessKey": "<your access key>",
"provider.bedrock.authentication.secretKey": "<your secret key>",
"provider.azureOpenAi.endpoint": "= ...",
"provider.azureOpenAi.authentication.apiKey": "<your api key>",
"provider.azureOpenAi.authentication.clientId": "= ...",
"provider.azureOpenAi.authentication.clientSecret": "<your client secret>",
"provider.azureOpenAi.authentication.tenantId": "= ...",
"provider.googleVertexAi.projectId": "= ...",
"provider.googleVertexAi.region": "= ...",
"provider.googleVertexAi.authentication.jsonKey": "= ...",
"provider.openai.authentication.apiKey": "<your openai api key>",
"provider.openaiCompatible.endpoint": "= ...",
"provider.anthropic.model.model": "= claude-3-5-sonnet-20240620",
"provider.bedrock.model.model": "= anthropic.claude-3-5-sonnet-20240620-v1:0",
"provider.azureOpenAi.model.deploymentName": "= ...",
"provider.googleVertexAi.model.model": "= ...",
"provider.openai.model.model": "= gpt-4o",
"provider.openaiCompatible.model.model": "= gpt-4o",
"data.systemPrompt.prompt": "= "You are **TaskAgent**, a helpful, generic chat agent that can handle a wide variety of customer requests using your own domain knowledge **and** any tools explicitly provided to you at runtime.
If tools are provided, you should prefer them instead of guessing an answer. You can call the same tool multiple times by providing different input values. Don't guess any tools which were not explicitly configured. If no tool matches the request, try to generate an answer. If you're not able to find a good answer, return with a message stating why you're not able to.
Wrap minimal, inspectable reasoning in *exactly* this XML template:
<thinking>
<context>…briefly state the customer’s need and current state…</context>
<reflection>…list candidate tools, justify which you will call next and why…</reflection>
</thinking>
Reveal **no** additional private reasoning outside these tags."",
"data.userPrompt.prompt": "= ...",
"data.memory.storage.storeType": "= ...",
"data.events.behavior": "WAIT_FOR_TOOL_CALL_RESULTS",
"provider.type": "anthropic",
"provider.anthropic.endpoint": "= ...",
})