Déployer des agents conversationnels

After designing and testing your conversational agent, you need to publish and deploy it to make it available to users. Publishing and deployment are two separate steps:

• Publishing: Packages your agent as a solution and uploads it to Orchestrator.
• Deployment: Makes the published solution available for execution with the required runtime resources.

Orchestrator folder requirements

Before publishing, ensure your target Orchestrator folder has the required resources configured.

Ressource	Objectif	Requis
Unattended robot account	Provides the execution identity for the conversational agent	Oui (Yes)
Serverless robot	Executes specific tool calls (cross-platform RPA automations)	If using these tools
Virtual machine	Executes Windows-based RPA automations	If using Windows automations
Connexions partagées	Provides access to Integration Service connectors	If tools use connectors

Important :

If your agent fails to start in Instance Management, verify that:

• An unattended robot account is assigned to the solution folder.
• You are in the correct tenant where the agent solution resides.

Publier

Publishing packages your conversational agent as a solution and uploads it to Orchestrator.

Publishing steps

1. In Studio Web, open your conversational agent.
2. Sélectionnez Publier dans la barre d'outils supérieure.
3. Select the target Orchestrator feed (we recommend Orchestrator tenant feed).
4. (Optional) Enter a Change log note describing your change.
5. Sélectionnez Publier.

For detailed publishing options, see Publishing a project.

Déploiement

After publishing, you need to deploy the solution to make it available for execution. Deployment associates the published solution with the runtime resources in your Orchestrator folder.

Étapes de déploiement

1. Navigate to your Orchestrator.
2. Locate the published solution.
3. Deploy (or upgrade) the solution, ensuring it has access to the required robot accounts and connections.

Once deployed, the agent appears in Instance Management and becomes available through configured channels.

For detailed deployment options, refer to Publishing a project.

Connection management

The agent needs access to the same connections used at design time. To ensure connections work at runtime, we recommend the following setup:

1. Créez des connexions Integration Service dans un dossier partagé Orchestrator.
2. Use these shared connections during design and debugging.
3. Publiez la solution en tant que sous-dossier dans le même dossier partagé.

This setup ensures the solution automatically inherits the parent folder's connections.

Remarque :

Personal connections are not currently supported. Only shared connections are available for conversational agents.

Deployment channels

After publishing, users can access your conversational agent through multiple channels. Each channel offers different capabilities and is suited for different use cases.

Channel overview

Canal	Idéal pour	Authentification de l’utilisateur
Gestion des instances	Admin testing, internal users	Compte UiPath
Autopilot for Everyone	Internal productivity hub	Compte UiPath
Microsoft Teams	Team collaboration	Microsoft account and UiPath account
Slack	Team collaboration	Slack account and UiPath account
iFrame embedding	Third-party apps and UiPath Apps	UiPath account or anonymous

Feature availability by channel

Not all chat features are available in every channel. Instance Management provides the complete feature set; other channels may have limitations.

Fonctionnalités	Gestion des instances	Autopilot for Everyone	Microsoft Teams	Slack	Iframe
Start new chat	✅	✅	✅	✅	✅
Historique du chat	✅	✅	✅	✅	✅
Delete chat session	✅	✅	✅	❌	✅
Paramètres	✅	✅	❌	❌	✅
Invites de démarrage	✅	❌	❌	❌	✅
Téléversements de fichiers	✅	✅	❌	❌	✅
Citations	✅	✅	✅	✅	❌
Aperçu HTML	✅	❌	❌	❌	✅
Copy response	✅	✅	❌	❌	✅
Feedback (thumbs)	✅	✅	✅	✅	✅
Debug dump (Ctrl+Alt+D)	✅	✅	❌	❌	❌

Choosing a channel

Consider these factors when selecting deployment channels:

Internal users with UiPath access

• Use Instance Management for admin testing and power users.
• Use Autopilot for Everyone as a central hub for all agents.

Team collaboration

• Use Teams or Slack to bring the agent where teams already work.

Custom applications

• Use iFrame embedding for third-party apps or UiPath Apps.

External or anonymous users

• Use iFrame embedding with anonymous auth server.

Chat session behavior

Conversational agents maintain persistent sessions:

• Each conversation runs as a dedicated Orchestrator process (active for up to 8 hours of inactivity).
• Sessions remain active to enable immediate responses.
• Idle sessions consume minimal resources.

Chat session behavior

Conversational agents maintain persistent sessions:

• Each conversation runs as a dedicated Orchestrator process (active for up to 8 hours of inactivity).
• Sessions remain active to enable immediate responses.
• Idle sessions consume minimal resources.

Using UiPath tools in external platforms

You can expose UiPath capabilities (automations, workflows, document processing) to external chat platforms like ChatGPT and Microsoft Copilot Studio using MCP (Model Context Protocol) tools. This approach uses direct tool calls rather than conversational agents.

For details on MCP integration, refer to MCP Servers.

Prochaines étapes

Select a channel to learn about setup and configuration:

• Gestion des instances
• Autopilot for Everyone
• Microsoft Teams
• Slack
• Apps embedding