IT OPS
AI Access-Policy Reviewer for Onboarding Requests
An agent reviews each onboarding access request against your written access policy, flags over-provisioned or unusual requests for IT, and auto-approves the rest.
How it runs
The automated pipeline, trigger to output.
- TriggerAccess request webhook receivedHTTP webhook
- ActionFetch access policy and baselinesNotion
- LogicAgent classifies standard vs anomalous
- ActionProvision standard requestsGoogle Drive
- ActionEscalate flagged requests to ITSlack
- OutputRecord rationale to policy logNotion
What it does
Puts a reasoning layer between the access request and provisioning. An agent compares each request to your access policy and recent peer grants, then either auto-approves a normal request or escalates an anomalous one with a written rationale.
When to use it
Use this when access requests are too varied for simple if-then mapping but too frequent for IT to review every one by hand. The agent catches scope creep, like a junior analyst requesting admin roles, without blocking routine hires.
How it works
- 1A webhook delivers the new access request with role, requested apps, and scopes.
- 2A Notion action retrieves the current written access policy and role baselines.
- 3The agent compares the request to the policy and to typical grants for the same role, classifying it as standard or anomalous with reasons.
- 4A logic branch routes standard requests to a Google Drive provisioning action and escalates anomalies.
- 5For escalations, a Slack action sends IT the request plus the agent's flagged concerns for a decision.
- 6The agent records its rationale to Notion for the audit record.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect NotionPages, databases, comments.
- 3Connect Google DriveDocs, sheets, slides, files.
- 4Connect SlackChannels, DMs, threads, mentions.
- 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
Recurring Sensor Fault Root-Cause Investigator
On a schedule, an agent reviews recent Monday work orders and BigQuery telemetry to identify equipment with repeating faults, drafts a root-cause hypothesis with a recommended fix.
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.
Agentic Inactive-Seat Reclamation Review
An agent investigates each idle SaaS seat by correlating SSO login gaps with HR status and ticket history, classifies it as reclaim, hold, or escalate, and drafts a reasoned…
Reconcile SSO logins against expense spend to find unmanaged tools
Joins SSO usage data with expense/payment records in Snowflake to surface tools that are being used but not paid for, or paid for but never logged.
Approved-Seat Deprovision Execution
Fires when an IT approver confirms a seat for removal, then executes deprovisioning via the IdP API and logs the action to an audit table and a Linear cleanup ticket.
HVAC Anomaly Detection to Severity-Routed Work Orders
Ingests building HVAC telemetry via webhook, flags out-of-band temperature, pressure, or runtime readings.
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.