Trigger Agents
A trigger is a configured way to invoke an agent without calling its API directly. Without a trigger, an agent only responds to direct calls against its API. Two trigger types are available:
-
A Microsoft Teams trigger connects the agent to Microsoft Teams. People in your organization chat with the agent in a personal Teams chat, and replies stream back as the agent produces them. See Connect an Agent to Microsoft Teams.
-
A schedule trigger runs the agent automatically on a recurring schedule. Each run sends a fixed message to the agent and is recorded as a transcript, with no reply path back. See Run an Agent on a Schedule.
Each trigger is its own resource on the agent, created, edited, and disconnected on its own, so you can attach several to the same agent. For example, one agent can serve a production Teams bot and a test Teams bot side by side, each through its own trigger.
| Triggers are available for Redpanda-managed agents only. A self-managed agent runs on your own infrastructure and is invoked through it, so it has no Triggers tab. To bring a self-managed agent into Agentic Data Plane for observability and governance, see Set up a self-managed agent. |
After reading this page, you will be able to:
-
Describe what an agent trigger is and how a trigger invokes an agent
-
Describe how triggers are added, edited, paused or disabled, and removed on an agent
-
Interpret the status that an agent’s Triggers tab reports for each trigger
Manage triggers
Triggers live on the agent’s detail page, on the Triggers tab. The tab presents them by type: Microsoft Teams triggers as cards, and schedule triggers as rows in a table. An agent with both gets a Channels heading over the cards and a Schedules heading over the table.
-
Click Add trigger, pick the trigger type, and fill in its configuration. A Microsoft Teams trigger takes the bot’s application (client) ID, directory (tenant) ID, and a secret store reference to the bot’s client secret. For the full setup, including the Microsoft side, see Connect an Agent to Microsoft Teams.
-
To read everything recorded about one trigger, including its full configuration and controls, click its name. For a Microsoft Teams trigger, that detail is already on its card.
-
To change a trigger’s configuration, select Edit trigger from the row’s actions menu, or edit a Microsoft Teams trigger on its card. The trigger’s unique ID, derived from its display name at creation, and the trigger’s type are fixed; the display name, description, and type-specific configuration stay editable.
-
To pause a schedule trigger without deleting it, turn off its Enabled switch in the table, and turn it back on to resume. Only schedule triggers have this control.
-
To remove a trigger, select Delete trigger from the row’s actions menu, or disconnect a Microsoft Teams trigger on its card. Removing it stops the agent from being invoked through that trigger and can’t be undone.
Narrow the list with the search box, which matches a trigger’s display name, description, ID, creator, and a schedule’s input message. Filter by Status to show only healthy, failing, paused, or pending triggers, and by Creator to show only the ones you created. Use the sort control, which reads out the order currently applied, to order by when each trigger was created, when it last ran, or when it runs next; the last-run and next-run options appear only when the agent has at least one schedule. To reload the triggers and their invocation history, click the refresh icon (Refresh now). The footer always carries the page controls and a rows-per-page selector, even when the agent has one trigger, none at all, or a filter that matches nothing, so you can set the page size before the list grows. Your browser remembers the page size you pick for the Triggers tab.
An agent with at least one schedule trigger also gets a summary row above the list: how many schedules are active out of the total, the success rate and failure count across each schedule’s recent invocations, how many scheduled fires were missed, and when the next run is due. These counts cover a recent window of runs per schedule rather than the schedule’s whole history, and success there means Redpanda accepted the invocation, not that the agent finished the work. The success rate weighs successful runs against failed ones only, so a missed fire counts in neither side of it and is reported on its own. An agent can therefore show a high success rate alongside a run of missed fires. While a schedule’s history is still loading, or if it can’t be read, the summary row says the data is partial.
Both trigger types also carry an enabled state that you can set with rpk ai trigger update --enabled in the Agentic Data Plane CLI, including where the card offers no control. A disabled schedule trigger fires no runs. A disabled Microsoft Teams trigger stops delivering messages to the agent, and Redpanda stops validating its bot credentials and stops updating its status. The card gives no sign that a Microsoft Teams trigger is disabled, and its status stays at the last reported check, so confirm the state with rpk ai trigger list, which shows whether each of the agent’s triggers is enabled.
To manage triggers from the terminal, or to keep them in Git, run the rpk ai trigger commands. See Use the Agentic Data Plane CLI and Manage Resources with GitOps.
A Microsoft Teams trigger also exposes a messaging endpoint: a URL that Teams delivers inbound messages to. Redpanda reports this URL on the trigger’s card shortly after you add the trigger, and you register it with your bot so Teams knows where to send messages.
Trigger status
Adding a trigger does not validate it on the spot. For a Microsoft Teams trigger, Redpanda’s messaging bridge checks each trigger in the background, about every 30 seconds, by validating its credentials with Microsoft, and reports the result. The Triggers tab shows one of three states:
-
Pending: No check has been reported yet. A trigger sits here briefly after you add it.
-
Connected: The latest check passed. For a Microsoft Teams trigger, this means Microsoft accepted the bot credentials.
-
Error: The latest check failed. The message on the card explains the reason, for example, a rejected client secret.
Because the check runs continuously, the status also catches problems that appear later: if a bot’s client secret expires, the trigger flips to Error without anyone sending a message. The tab refreshes the status on its own, and you can also refresh on demand with the refresh icon (Refresh now).
A schedule trigger reports the outcome of its runs rather than a connection check. Its row shows the last invocation’s outcome and how long ago it was due, a bar per run for its last 10 invocations, and the estimated next run time, which reads Paused for a disabled schedule. A trigger whose status check failed carries an error badge next to its name. The same reading drives the Status filter, so filtering on failing finds both a trigger whose credentials were rejected and a schedule that is still enabled and whose latest run failed or was missed. A paused schedule reads as paused whatever its last run did, so pausing a failing schedule moves it out of the failing filter. For the outcomes a run can have, see Run an Agent on a Schedule.
