Settings → Agents is the hub where you build the AI agents your team will actually use, decide which ones are personal vs shared with the workspace, and browse Pod's catalog of pre-built templates. It's where your agent library lives — not where agents run on a deal, and not where you schedule them to run automatically.

For the runtime, see Launch and use AI agents. For automated runs on a schedule or trigger, see Set up agent triggers (which now lives under Settings → Automations).

How to access

Open Pod in the web app.
Go to Settings.
Select Agents.

Settings → Agents is web-app only. Deep links that point here from inside the Chrome Extension open Pod in a new browser tab at the same place.

The two tabs

The page has two tabs:

Your Agents — every Personal and Org agent your workspace has today. This is where you build new agents, open existing ones to edit, duplicate, or remove them, and see how many automations each one is driving.
Library — Pod's curated catalog of pre-built agent templates. Browse, preview, and import any template to make it your own.

The Your Agents tab

What you'll find

The tab groups your agents into two sections:

Personal Agents — agents only you see and run.
Org-Wide Agents — agents shared across the whole workspace; everyone in the workspace can see and run them. Only workspace admins can create, edit, or remove them.

Use the filter at the top to show All, Personal Agents, or Org-Wide Agents only. The tab title shows the total agent count.

What an agent card shows

Each agent card shows the information you need to decide what to do next:

The agent's title and description.
Whether Browser (web search) is on or off.
How many automations are attached to the agent.
Quick actions on the right: Add Trigger, Edit, and an overflow menu with Duplicate and (when allowed) Remove.

Click anywhere on the card to open the agent in the AI Agent Builder drawer.

Build a new agent

From Your Agents, click Build New Agent.
The AI Agent Builder drawer opens. Fill in title, description, prompt, response format, and whether to enable web search.
If you're a workspace admin, choose whether the agent is Personal (just you) or Org-Wide (everyone in the workspace).
Save.

For a full walkthrough of writing a strong prompt and response format, see Build a new agent and the AI Agent Best Practices Guide.

Edit an agent

Click the agent's card, or click the Edit icon on the right.
The drawer opens in edit mode with the agent's current configuration.
Change whatever you need, then save.

Editing a Personal agent is available to whoever created it. Editing an Org agent is available to workspace admins.

Duplicate an agent

From the overflow menu (⋯) on an agent card, click Duplicate. Pod creates a copy in your Personal agents named <Original title> - Copy. Use this when you want to fork an existing agent (yours, or an Org agent your admin built) into a Personal variant you can tweak without affecting the shared one.

Remove an agent

From the overflow menu (⋯), click Remove. Removing is permanent and can't be undone. You'll be asked to confirm.

You can remove any Personal agent you own.
Only workspace admins can remove Org agents.

The Library tab

The Library tab is where you browse Pod's pre-built agents — ready-made templates for the workflows we see most often across customers (deal reviews, meeting prep, follow-ups, CRM hygiene, and more). Pre-built agents are not live in your workspace until you import them.

Browse the Library

Use the category chips across the top to narrow by workflow (for example, deal review, follow-up, CRM).
Use the search bar to filter by agent title or description.

Click any card to preview the agent.

Preview a pre-built agent

Selecting a card opens a read-only drawer showing the agent's title, description, full prompt, response format, and whether web search is enabled. You're seeing the template exactly as Pod authored it — nothing is saved to your workspace yet.

Import a pre-built agent

In the read-only preview, click Import.
The drawer reopens in create mode, prefilled with the template's content.
Adjust anything you want — rename it, edit the prompt, tweak the response format, turn web search on or off.
By default the imported agent is created as a Personal agent. If you're a workspace admin, switch the agent type to Org-Wide before saving to share it with the whole workspace.
Save.

The imported agent lands in your Your Agents tab as a brand-new Personal or Org agent. From that point on, it behaves exactly like an agent you built from scratch — it shows up in the agent picker on every deal, and you can attach triggers to it from Settings → Automations.

Importing is the one-time bridge from template to live agent. Pre-built agents are not runnable directly from the Library or the agent picker — they have to be imported first.

Personal agents vs. Org agents

Personal agents are yours. Only you see them in the picker and in Your Agents. Building, editing, duplicating, and removing are up to you.
Org agents are shared with everyone in the workspace. Only workspace admins can create, edit, or remove them, but every user can see and launch them on their deals.

When you're not sure which to use, start Personal. You (or an admin) can always duplicate it or rebuild it as an Org agent later.

Where triggers live now

Automated runs — running an agent on a schedule, on a CRM event, or on a trigger — live on a separate Settings page: Settings → Automations. The ⚡ (bolt) icon on each agent card is a shortcut into that flow.

For the full walkthrough of setting up, editing, and monitoring triggers, see Set up agent triggers.

When to use this page vs. other AI agent pages

Use Settings → Agents when you want to build, organize, or import the agents themselves.

Go to these related pages when your goal is different:

Use Build a new agent when you want a deep walkthrough of writing a strong prompt and response format.
Use Launch and use AI agents when you want to run or continue an agent on a live deal.
Use Set up agent triggers when you want an agent to run automatically on a schedule or a trigger.
Use Use the Agent Feed when you want to review results from automated runs in one place.
Use Manage agent actions when you want to approve, reject, or troubleshoot the specific actions agents take on your behalf.
Use Connect MCP servers when you want to give your agents new tools to act on external systems.
Use the AI Agent Best Practices Guide when you want help making your agents better over time.