Skip to main content

Managing AI Agents

Manage your AI Agents in Productive: configure their details, triggers, instructions, connectors, skills, and permissions, review their activity, and share or deactivate them.

This article covers how to manage an Agent once you've created it: configure its settings, review its activity, control what it can do, and share it with others.

👉 Haven't created an Agent yet? Start with Setting Up AI Agents.

AI Agents are available on the Ultimate subscription plan.

The Agents List

Go to Resourcing > Agents to see all your Agents.

Adjust the view by adding fields and applying filters the same way you would in other list views in Productive.

Click on any Agent to open its profile. The profile is organized into four tabs: Info, Activity, Projects, and Permissions.

Info Tab

The Info tab contains the Agent's details, triggers, instructions, connectors, and skills.

Agent Details

  • Description: A short summary of what the Agent does. Shown in the Agents list to help others quickly identify its purpose.

  • Manager: The person responsible for the Agent, usually its creator. Used for the organizational chart and any agent-related approval flows. Only the Agent's manager can edit its settings.

  • Model: The model the agent runs on. Defaults to Auto, which lets Productive pick the most efficient model for each run. The dropdown lists every model available to you.

  • Thinking effort: How much the agent reasons before acting. Auto matches the effort to the run; Low is fastest and lightest on credits, and High is more thorough but slower. Medium sits between the two.

📌 If your admin has restricted which models your organization can use, you'll only see the approved ones. See AI Models.
​

📌 More advanced models and higher thinking effort can use more AI credits. Agents on a trigger run on their own, so the difference compounds. Track it in Settings > Usage.
​

Triggers

Triggers define when the Agent runs automatically, without the need to start it manually.

Click + Trigger on the Info tab to add one.

👉 For the full setup, including trigger types, conditions, and per-trigger instructions, see Setting Up Triggers for AI Agents.

Instructions

Instructions define how the Agent behaves, what rules it follows, what it focuses on, and how it handles specific situations.

The Agent's initial instructions are written by the Assistant during setup. You can edit them manually here at any time, or update them by prompting the Assistant directly.

Connectors

Connectors give the agent access to external tools and services. Once connected, the agent can use them to read data or take actions in those systems as part of its work.

To add a connector, go to the Info tab and click + Add connector. You can disconnect a connector at any time from the same section.

📌 You can only add connectors you've already connected to your own account.

📌 Connectors are added and managed by the agent's manager only. Users the agent has been shared with can see which connectors are active but cannot add or remove them.

👉 To connect your account to a connector and learn how to manage them, see Connectors.

Skills

Skills are reusable instruction sets that extend how an agent behaves — additional context, process guidelines, or domain-specific rules that don't need to be part of the main instructions.

To assign a skill to an agent, click + Skill on the Info tab and choose from the list. An agent can have multiple skills at once, and all active skills are always on — the agent follows them on every run, whether triggered on a schedule or started through the AI Assistant.

👉 For more on creating, managing, and sharing skills, see What Are Skills?

Activity Tab

The Activity tab shows what the Agent has been doing. It's split into two sections:

  • Work Log: A chronological record of all actions the Agent has taken in Productive.

  • Feed: Changes and updates related to the Agent's profile and settings.

Use this to stay informed about what the Agent is doing and review its activity history at any time.

Projects Tab

Shows the projects the Agent has been added to as a member. You can also add the Agent to additional projects directly from this tab.

Permissions Tab

The Permissions tab is where you assign permissions to the agent. This determines what types of actions the agent is allowed to perform — creating tasks, updating records, managing time entries, and so on.

Once the Agent is created, it starts with a copy of your permissions by default, so it can begin working right away. You can adjust permissions at any time after the initial setup.

To configure the agent's permissions, click Edit Permissions.

📌 Only the agent's manager can edit permissions.

The available permissions are limited to those the agent's manager holds. If the manager doesn't have a certain permission, it won't be available to assign to the agent.

👉 For a full list of available permissions, see Permission Groups and Permissions.

📌 If a permission is assigned but the manager later loses it, that permission will no longer apply. You'll see a warning directly on the affected permission. Before saving any new changes, make sure to manually disable any flagged permissions.

Sharing Agents

By default, Agents are private — only you can see and use them. To make an Agent available to others, click Share on the Agent's profile.

Select the users you want to share the agent with and click Add.

Additional Options

Click the three-dot menu on the Agent's profile to access additional actions.

From here, you can:

  • Edit profile: Update the Agent's name and avatar.

  • Deactivate: Turns the Agent off. To reactivate a deactivated Agent, filter the Agents list to show deactivated Agents, then open the three-dot menu and select Activate.

👉 Head to Working With AI Agents to learn how to interact with your Agent, assign it to tasks, and get the most out of it.

Did this answer your question?