IT OPS
Multi-signal incident triage to severity-graded draft
An agent correlates near-simultaneous Datadog and Cloudflare alerts into one incident, grades severity, drafts a single status update, and posts it to Discord for approval.
How it runs
The automated pipeline, trigger to output.
- TriggerDatadog alert opens correlation windowDatadog
- ActionPull related Cloudflare alertsCloudflare
- LogicCorrelate signals and grade severity
- ActionDraft unified status update
- ActionPost draft to Discord for approvalDiscord
- OutputPublish update to status pageHTTP webhook
What it does
When alerts arrive from both Datadog and Cloudflare close together, an agent correlates them into a single incident instead of letting each fire its own message. It grades overall severity from the combined signals, drafts one coherent status update in the right tone, and routes it to Discord for approval.
When to use it
Use it when one real outage lights up multiple monitors at once and you want a single, accurate customer message rather than three conflicting ones. The agent decides whether signals belong to the same incident.
How it works
- 1A Datadog alert webhook starts the workflow within the correlation window.
- 2The agent pulls related recent Cloudflare alerts to judge whether they describe the same incident.
- 3It grades severity and decides scope from the merged signals.
- 4An agent step drafts one unified status update matched to that severity.
- 5The draft posts to Discord for approval, then publishes to the status page via HTTP webhook.
Set it up
What you configure once, before turning it on.
- 1Connect DatadogMetrics, traces, log search.
- 2Connect CloudflareWorkers, Pages, R2, KV — the edge stack.
- 3Connect DiscordCommunity channels + voice + bots.
- 4Connect HTTP webhookTrigger any URL on agent actions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More IT Ops workflows
Daily Building Anomaly Digest to MS Teams
Each morning queries BigQuery for the prior day's flagged sensor anomalies, summarizes them by site and system into a ranked briefing.
Indoor Air Quality Breach to Tenant Notice and Work Order
Listens for CO2, VOC, or humidity sensor alerts via webhook, and when a zone exceeds occupant-safety limits it emails affected tenants, opens a Monday remediation task.
Self-Service Reclaim Email for Idle Users
Detects users idle in a SaaS app past the threshold and emails each one a keep-or-release link; unanswered seats after the deadline are auto-flagged for removal.
Outlook Room Conflict Resolver with Approval Gate in Teams
When an Outlook room clashes, proposes a rebooking and asks the bumped meeting's organizer to approve the move in Microsoft Teams before any change is made.
Outlook Room Double-Booking Resolver with Auto-Rebook
Detects when two meetings claim the same Outlook room resource and automatically relocates the lower-priority meeting to a comparable free room.
Monthly Wasted-License Cost Report
Aggregates inactive-seat data across all tracked SaaS apps each month, computes total reclaimable spend, and delivers a ranked cost report to leadership in Notion and Slack.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.