IT OPS
Agent-Orchestrated Offboarding Deprovision Plan
A CEO-led offboarding agent reads the leaver's role and access footprint, drafts a tool-by-tool deprovision plan with risk ordering, executes the revocations.
How it runs
The automated pipeline, trigger to output.
- TriggerManager opens offboarding request in CEO chat
- ActionQuery Postgres for role, grants, and owned resourcesPostgres
- LogicDraft risk-ordered plan; gate shared/billing seats for approval
- ActionExecute GitHub admin and org access revocationsGitHub
- OutputReport completed and pending-signoff items to SlackSlack
What it does
Hands offboarding to an agent that reasons about the specific person rather than running a fixed checklist. It assembles the leaver's full access footprint, decides the safest revocation order (high-risk admin access first), carries out the deprovisioning, and escalates anything ambiguous to a human.
When to use it
Use it for senior or admin-heavy departures where blanket revocation is risky and you want judgment about sequencing, shared-account handling, and what genuinely needs a manager's approval before being cut.
How it works
- 1A manager opens an offboarding request in chat naming the departing employee.
- 2The agent queries Postgres for the person's role, access grants, and owned resources.
- 3It drafts a risk-ordered deprovision plan, revoking GitHub admin and org access first.
- 4A logic gate holds any shared-account or billing-owner seat for explicit approval.
- 5The agent executes the approved revocations tool by tool.
- 6It returns a completion report to Slack listing what was deprovisioned and what awaits sign-off.
Set it up
What you configure once, before turning it on.
- 1Connect PostgresAny Postgres URL — query, write, migrate.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More IT Ops workflows
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.
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.
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.
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.
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.
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.