> ## Documentation Index
> Fetch the complete documentation index at: https://docs.meetsquad.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent triggers

> What makes an agent run: a schedule, a workspace event, or an event from a connected integration.

A trigger is what makes an agent run. Three kinds ship: a recurring schedule, a workspace event, and an event from a connected integration. An agent can carry several at once.

<CardGroup cols={3}>
  <Card title="Recurring" icon="clock">
    A schedule on one of six cadences, from hourly to annually.
  </Card>

  <Card title="Workspace" icon="layout-grid">
    Five events from things happening inside Squad.
  </Card>

  <Card title="Integrations" icon="plug">
    Thirteen events across seven connected providers.
  </Card>
</CardGroup>

**Add trigger** opens a two-pane dialog. The left column groups what is available under **Recurring**, **Workspace**, and one group per connected integration that offers triggers. The right pane configures whatever you picked. Each trigger you add lands as a summary row with an X to remove it.

A schedule is optional. An agent can run purely on events, purely on a clock, or on both.

<Note>
  What an agent cannot do is run on nothing. Removing or pausing an agent's last active trigger is refused.
</Note>

## Schedule

One option, **On a schedule**, under **Recurring**. Pick a frequency and, optionally, when it starts.

Six cadences: **Hourly**, **Daily**, **Weekly**, **Monthly**, **Quarterly**, **Annually**. Monthly and longer cadences clamp the anchor day, so a schedule anchored on the 31st still fires in February.

**Starts** takes a date and a time. Set it and the first run happens then, repeating on the cadence from there. Leave it unset and the agent starts within the hour, then repeats.

<Note>
  An agent gets at most one schedule. Once it has one, the **On a schedule** option in the dialog is greyed out. To change the frequency, edit the schedule row you already have.
</Note>

## Workspace events

Five events fire from things happening inside Squad.

<AccordionGroup>
  <Accordion title="Knowledge created" icon="file-plus">
    Fires when a document is added to the [knowledge base](/knowledge-documents). Takes an optional scope: watch a folder, watch a single document, or leave it open and watch everything. The document that changed is handed to the agent as context for that run.
  </Accordion>

  <Accordion title="Knowledge updated" icon="file-pen">
    Fires when a document in the [knowledge base](/knowledge-documents) is edited. Takes the same optional scope as **Knowledge created**: a folder, a single document, or everything. The document that changed is handed to the agent as context for that run.
  </Accordion>

  <Accordion title="Competitor created" icon="building-2">
    Fires when a competitor document is added. Takes no scope.
  </Accordion>

  <Accordion title="Competitor updated" icon="building-2">
    Fires when a competitor document changes. Takes no scope.
  </Accordion>

  <Accordion title="Insight created" icon="lightbulb">
    Fires when a new [insight](/insights) surfaces from your signals. It takes an optional **Minimum score** between 0 and 1, so the agent only wakes for insights at or above the bar you set. Leave it blank to fire for all of them. Values outside the range are clamped, so a typed `2` becomes 1 rather than a trigger that never fires.
  </Accordion>
</AccordionGroup>

## Integration events

Thirteen events across seven providers. A provider's group only appears in the dialog once that integration is connected, and only if it declares agent triggers. Connect one first from [Integrations](/integrations).

| Provider                         | Events                                                            |
| -------------------------------- | ----------------------------------------------------------------- |
| [Notion](/integrations/notion)   | Page updated                                                      |
| [Gong](/integrations/gong)       | Call recorded                                                     |
| [Linear](/integrations/linear)   | Issue created, Issue updated, Comment added                       |
| [GitHub](/integrations/github)   | Issue opened, Pull request merged                                 |
| [PostHog](/integrations/posthog) | Event captured                                                    |
| [Jira](/integrations/jira)       | Request created, Comment added, Request updated, Request resolved |
| [Fellow](/integrations/fellow)   | Note generated                                                    |

Where a provider supports it, the right pane lets you narrow the trigger to a specific scope, for example a single Notion page rather than every page in the sync. The thing that fired the trigger is passed to the agent as context, the same way a workspace event is.

<Warning>
  Slack declares no agent triggers, by design. A Slack message never starts an agent run. A workspace whose only connected integration is Slack sees no integration group in the trigger dialog at all, which is the expected state and not a broken one. Slack still works as a place an agent can read from and as a delivery channel for reports. See [Tools and access](/agent-tools-access).
</Warning>

<Warning>
  Agents cannot trigger other agents. There is no chaining, no "when agent A finishes, run agent B", and no way to build one. If you need two stages, write them as one agent with instructions covering both, or give the second agent a trigger on something the first one produces, such as **Knowledge created** scoped to the folder the first agent writes to.
</Warning>

## Editing triggers later

The **Triggers** section on an agent's detail page is the same builder. Add, reconfigure, or remove triggers there at any time. Removing the last active one is refused, so pause the agent instead when you want it to stop entirely.