SECOPS
Agent-triaged IAM grant investigations into Linear
An AI agent investigates each suspicious IAM grant by pulling actor context and recent activity, decides whether it is benign or needs follow-up.
How it runs
The automated pipeline, trigger to output.
- TriggerWebhook: flagged IAM grantHTTP webhook
- ActionAgent enriches actor + policy contextOpenAI
- LogicAgent assigns verdict
- LogicRoute by verdict
- OutputFile triaged Linear issueLinear
What it does
When a suspicious IAM grant is reported via webhook, an agent gathers context — who the actor is, their recent grant history, the sensitivity of the policy, and whether the change matches an open change request — then reasons about intent. It classifies the grant as benign, needs-review, or likely-malicious and opens a Linear issue pre-filled with its findings and a recommended next step.
When to use it
Use this when your team drowns in low-signal IAM alerts and needs a first-pass analyst that triages before a human looks. The agent handles the tedious context-gathering so engineers only open tickets that already have a verdict and evidence attached.
How it works
- 1An inbound webhook delivers a flagged IAM grant event and triggers the run.
- 2The agent enriches the event with actor identity, grant history, and policy sensitivity.
- 3The agent reasons about whether the grant fits a legitimate pattern and assigns a verdict.
- 4A logic step routes by verdict: benign grants are logged and closed; the rest proceed.
- 5A Linear issue is created with the verdict, evidence, and recommended action, labeled by severity.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect LinearIssues, projects, cycles, triage.
- 3Connect OpenAIModels, embeddings, files.
- 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 SecOps workflows
Compile a weekly WAF tuning review with trends to Confluence
Every week an agent rolls up Cloudflare WAF block clusters by rule and ASN, compares them to prior weeks for trend direction.
Sensitive Dropbox Link Owner Remediation Loop
When a newly created Dropbox shared link points to a sensitive file, this workflow DMs the file owner, gives them a deadline to justify or revoke it.
Post-Revocation Verification and Audit Logging
After a key is revoked, it confirms the old credential actually fails, verifies the replacement works.
Exposed-Secret Incident Triage and Remediation Agent
An agent-driven workflow that investigates a reported leaked secret end to end, decides revoke-versus-escalate, executes the rotation.
Page on-call when a WAF rule mass-blocks legitimate traffic
On demand or every few minutes, it detects a single Cloudflare WAF rule suddenly blocking a broad spread of ASNs and paths (a likely false-positive storm).
PII Content Scan on New Dropbox External Share
When a file gets an external Dropbox link, it reads the file content, uses an AI classifier to detect PII or secrets.
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.