Automations Three ways to fire an agent.
Run an automation on demand, on a schedule or from a webhook. Pick per automation, based on how you want the work to run.
Three ways to fire an agent.
Each mode is a real system, not a checkbox. Pick per agent based on how you want the workflow to run.
On-demand
When to use it
- Operator-initiated triage or investigation
- One-click reporting at the moment you need it
- Ad-hoc “pull context” requests
- Testing a new agent before promoting out of dry-run
Scheduled
When to use it
- Daily ticket review, weekly briefings, nightly hygiene
- Recurring drift, backlog, or audit checks
- Anything where “always at 7am” matters
Timezone-aware cron. A run that cannot start waits in a queue, and a run that waits too long is marked Skipped at no cost.
Webhook
When to use it
- Event-driven follow-up (new ticket, alert, PagerDuty)
- Kicking off context gathering right when something happens
- Bridging external systems into your workflows
Per-agent webhook secret, configurable payload modes (none / full / selected fields), payload size cap, and 10 hits/minute per-agent rate limit.
| On-demand | Scheduled | Webhook | |
|---|---|---|---|
| Fires from | Portal, or your AI assistant through StackJack’s MCP tools | Timezone-aware cron | Signed HTTP POST |
| Input payload | Operator context | None (instructions in prompt) | None / full / selected fields |
| Rate limit | Human-paced | Your cron | 10 / min per agent |
Questions.
How are webhook endpoints secured?
Each webhook-triggered agent gets its own signed secret baked into the URL. There’s a per-agent rate limit (10 / minute), a payload size cap, and three payload modes: none (prompt-driven), full payload, or selected fields. You control exactly what context the agent sees.
What happens to a scheduled run when I am out of credits or all slots are busy?
If all your slots are busy, the run waits in a queue and starts when a slot frees. If its wait ends first, the run is marked Skipped, costs nothing, and the next scheduled time runs as normal. If your balance cannot cover a run, the run is recorded as Out of credits with nothing charged, and you can have StackJack email you when a run fails.
Keep reading.
For depth, in the docs: On-demand and scheduled triggers · Webhook triggers
Recurring work, managed.
Automations are available today for every StackJack user. Run them on your Azure Foundry or your own Anthropic key for a flat monthly rate, or buy a credit pack to try one. Packs never expire, and you see real-time usage against your balance as your agents run.