- 概要
- UiPath GenAI アクティビティ
- Act! 365
- ActiveCampaign
- Adobe Acrobat Sign
- Adobe PDF Services
- Amazon Bedrock
- Amazon Connect
- Amazon Polly
- Amazon SES
- Amazon Transcribe
- Anthropic Claude
- Asana
- AWeber
- Azure AI Document Intelligence
- Azure Maps
- BambooHR
- Box
- Brevo
- Calendly
- Campaign Monitor
- Cisco Webex Teams
- Citrix ShareFile
- Clearbit
- Confluence Cloud
- Constant Contact
- Coupa
- CrewAI – プレビュー
- Customer.io
- Databricks Agent
- Datadog
- DeepSeek
- Deputy
- Discord - プレビュー
- DocuSign
- Drip
- Dropbox
- Dropbox Business
- Egnyte
- Eventbrite
- Exchangerates
- Expensify
- Facebook
- Freshbooks
- Freshdesk
- Freshsales
- FreshService
- Getresponse
- GitHub
- Google マップ
- Google Speech-to-Text
- Google Text-to-Speech
- Google Vertex
- Google Vision
- GoToWebinar
- Greenhouse
- Hootsuite
- HTTP Webhook
- HubSpot CRM
- Hubspot Marketing
- IcertisIcertis
- iContact
- Insightly CRM
- Intercom
- Jina.ai
- Jira
- Keap
- Klaviyo
- LinkedIn
- Mailchimp
- Mailjet
- MailerLite
- Mailgun
- Marketo
- Microsoft Azure OpenAI
- Microsoft Azure AI Foundry
- リリース ノート
- About the Microsoft Azure AI Foundry activities
- Execute the thread
- Microsoft Dynamics CRM
- Microsoft Power Automate
- Microsoft Sentiment
- Microsoft Teams
- リリース ノート
- Microsoft Teams アクティビティについて
- プロジェクトの対応 OS
- チャンネルを作成
- チャネルにメンバーを招待
- すべてのチャネルのリストを取得
- 個々のチャット メッセージを送信
- チャネル メッセージに返信
- オンライン Teams 会議を作成
- チャネル メッセージを送信
- グループ チャット メッセージを送信
- 名前でチャネルを取得
- 個々のチャットを取得
- 名前でチームを取得
- ユーザーをチームに招待
- すべてのチャネル メッセージのリストを取得
- すべてのチャット メッセージのリストを取得
- すべてのチーム メンバーのリストを取得
- オンライン Teams 会議を取得
- すべての記録のリストを取得
- すべてのトランスクリプトのリストを取得
- 会議のトランスクリプト/記録をダウンロード
- すべてのレコードのリストを取得
- レコードを挿入
- レコードを更新
- レコードを取得
- レコードを削除
- テクニカル リファレンス
- Microsoft Translator
- Microsoft Vision
- Miro
- Okta
- OpenAI
- OpenAI V1 準拠の LLM
- Oracle Eloqua
- Oracle NetSuite
- PagerDuty
- Paypal
- PDFMonkey
- Perplexity
- Pinecone
- Pipedrive
- QuickBooks Online
- Quip
- Salesforce
- Salesforce Marketing Cloud
- SAP BAPI
- SAP Cloud for Customer
- SAP Concur
- SAP OData
- SendGrid
- ServiceNow
- Shopify
- Slack
- SmartRecruiters
- Smartsheet
- Snowflake
- Snowflake Cortex
- Stripe
- Sugar Enterprise
- Sugar Professional
- Sugar Sell
- Sugar Serve
- TangoCard
- Todoist
- Trello
- Twilio
- IBM WatsonX
- WhatsApp Business
- WooCommerce
- Workable
- Workday
- Workday REST
- X(旧ツイッター)
- Xero
- Youtube
- Zendesk
- Zoho Campaigns
- Zoho Desk
- Zoho Mail
- Zoom
- ZoomInfo

Integration Service のアクティビティ
This activity enables automated processes orchestrated by Maestro to connect to an Azure AI Foundry project and invoke agents defined inside it.
projectname/services.ai.azure.com/api/
.
A strategy for Maestro to agent interaction should persist throughout agent creation. In the Maestro business process, Maestro will send a pre-defined set of parameters to the agent with a clear expectation of which parameters the agent will use in its reply back to continue driving the process to its goal.
To use this activity in a Maestro agentic process, follow these steps:
- Add a service task element to the canvas and open the task's Properties panel.
- Name the service task
Foundry Hello World
. - In the Implementation section, from the Action dropdown list, select Start and wait for external agent.
- Select the Microsoft Azure AI Foundry connector.
- Select an existing connection or create a new one. For more information, see Microsoft Azure AI Foundry authentication.
-
From Activity, select Execute the thread.
- From Agent Name, select an agent previously created in Microsoft Azure AI Foundry.
-
In Message, enter "What can you do?". Make sure to include the quotes in the prompt.
-
Connect the start event to the service task, and the service task to an end event node in the canvas.
-
Select Debug to run this process. After a successful run, review the global variables and look for the {:} response from the source: Foundry Hello World. Take note of the structure of the reply.
Note: Foundry agent execution may take up to 90 seconds to complete. In some rare situations, it can take up to 10 minutes due to the Foundry agent’s asynchronous response mechanism.For example, this is the agent's response to the prompt "What can you do?":
{ "content_value": "Here’s how I can assist you:\n\n- **Recommend AI Tools**: Suggest the best AI tools (apps, platforms, APIs) for your specific challenge, need, or workflow.\n- **Usage Guidance**: Provide clear steps on how to use the suggested AI tool for your scenario.\n- **Prompt Writing**: If the suggestion involves an AI language model (like ChatGPT, Claude, etc.), I provide you with a ready-to-use prompt tailored to your need.\n- **Comparison**: Offer quick comparisons between similar AI tools if needed.\n- **Special Cases**: Point you to tools with image/audio/video capabilities for media-related requirements.\n\n**Try me:** \n- State your problem, task, or goal (e.g., “I need to summarize research articles”).\n- I’ll reply with the best matching AI tool and exact usage instructions/prompt.", "thread_id": "thread_AJhKo6PvrzCFu1dtpXV1ZEqM", "assistant_id": "asst_lozoOWbsiggHu9QItxfrXZt1", "role": "assistant", "run_id": "run_GS5b1gEgXElhudrhFSAtFzQo", "content_type": "text", "latest_message_id": "msg_D5MUkFj4AvsHKNdHNFQBJpAv", "created_at": 1758581230, "object": "thread.message", "timestamp": "2025-09-22T22:47:10Z", "eventType": "TRIGGER_CREATED" }
{ "content_value": "Here’s how I can assist you:\n\n- **Recommend AI Tools**: Suggest the best AI tools (apps, platforms, APIs) for your specific challenge, need, or workflow.\n- **Usage Guidance**: Provide clear steps on how to use the suggested AI tool for your scenario.\n- **Prompt Writing**: If the suggestion involves an AI language model (like ChatGPT, Claude, etc.), I provide you with a ready-to-use prompt tailored to your need.\n- **Comparison**: Offer quick comparisons between similar AI tools if needed.\n- **Special Cases**: Point you to tools with image/audio/video capabilities for media-related requirements.\n\n**Try me:** \n- State your problem, task, or goal (e.g., “I need to summarize research articles”).\n- I’ll reply with the best matching AI tool and exact usage instructions/prompt.", "thread_id": "thread_AJhKo6PvrzCFu1dtpXV1ZEqM", "assistant_id": "asst_lozoOWbsiggHu9QItxfrXZt1", "role": "assistant", "run_id": "run_GS5b1gEgXElhudrhFSAtFzQo", "content_type": "text", "latest_message_id": "msg_D5MUkFj4AvsHKNdHNFQBJpAv", "created_at": 1758581230, "object": "thread.message", "timestamp": "2025-09-22T22:47:10Z", "eventType": "TRIGGER_CREATED" }
The agent’s output must be assigned to a process variable so it can influence the progress of the Maestro process, for example to make a decision based on a boolean evaluation, or to use the answer from a classification task.
-
In Design mode, select the agent from the design canvas.
-
Select Properties.
-
Under Output, select Add new and add a variable of type String named agent_reponse.
-
For Value, select Foundry Hello World > Response > Content value (string).
Example of handling agent output in Maestro using the Expression editor:
If the prompt was:
"What is the capital of France?" answer in a JSON only on the form of {"capital":"Normandy") only JSON output
string
):
{"capital":"Paris"}
answer_in_JSON
and use the Expression editor:
js:JSON.parse(result.response.messages[0].content)
JSON
):
{
"capital": "Paris"
}
{
"capital": "Paris"
}
Beyond establishing connectivity, you should test prompts both in the Microsoft Azure AI Foundry workspace as well as from Maestro. This ensures you achieve the desired output that can best be consumed by Maestro, assigned to variables, and passed on to other actors in the process.
We recommend that detailed prompts remain within the system prompts of the agent within Microsoft Azure AI Foundry. The user prompt which is provided by Maestro to the agent at runtime should be brief and to the point. Its role is primarily to indicate the relevant variables needed by the agent to perform a specific tasks and generate an expected consistent output.
"What is the quantity on inventory of Order ID " + vars.orderId_1 + "respond only with a JSON object with the quantity in the key Order_Quantity. No explanations, only JSON"
"What is the quantity on inventory of Order ID " + vars.orderId_1 + "respond only with a JSON object with the quantity in the key Order_Quantity. No explanations, only JSON"
The agent will reply with:
{"Order_Quantity":"100"}
{"Order_Quantity":"100"}
JSON
, it may actually be of type string
.