Scheduled Triggers
Run an agent on a schedule
You'll be able to
- Attach a schedule to an agent so it runs without a human kicking it off
- Choose a cadence and a guard so unattended runs stay safe
Read first
Day 4 Lab
**Status: Generally available — Glean’s Agent Builder and its core features (scheduled triggers, versioning, native actions) are GA. Only the *content triggers* trigger type remains Beta; confirm availability in your tenant.**
- Take your reviewed agent and choose a cadence: hourly, daily at 8am, weekly Monday.
- Attach the schedule as a trigger so the agent runs without anyone starting it.
- Add a guard that makes an empty run a no-op (no input -> send nothing).
- Decide where a failed run reports — a DM or channel, so silence never means "fine."
- Note the first run time and confirm the window matches what you intended.
Working Example: Attaching a Schedule
Per Glean's Fall '25 launch announcement, an agent can carry a scheduled trigger that runs it on a cadence with no human in the loop. Verified against fall25_launch.
Agent: "Morning #incidents digest"
Trigger: schedule
Cadence: every weekday at 08:00 (tenant timezone)
Window: posts since the previous run
Guard: if zero new posts -> stop, send nothing
On error: DM #ops-alerts with the failure reason (don't fail silently)
First run: tomorrow 08:00. Unattended from then on.A schedule turns a one-off into an unattended worker, which raises the stakes: a bad run now repeats on a timer. The guards — an empty-run no-op and a loud failure path — are the MANAGE controls that keep an automated cadence from compounding a mistake. Scheduled triggers are an announced feature; verify they exist and fire reliably in your tenant before you trust an unattended cadence.
Check for understanding
An agent runs unattended on a schedule. Name one guard that keeps a bad run from compounding.
Check yourself
1. In Glean's vibe-code agent builder, how do you start building an agent?
2. The vibe-code builder, 100+ native actions, scheduled triggers, looping, and versioning are best described as...
3. Before adding a native WRITE action (e.g., update a Salesforce case) to an agent step, what should you check?
4. An agent runs unattended on a daily schedule. Which guard most directly keeps a bad run from compounding?
5. Why does rolling an agent back to a known-good version count as a governance control?
In 10 seconds
“Glean's Fall '25 launch announced scheduled triggers: an agent that fires on a cadence, no human in the loop. Pick the right interval — and a guard — so an unattended run can't quietly go wrong.”
Looping Over Data