AI AGENTS
HuggingFace Gating-Change Detector with GitLab Issue Escalation
Checks whether any pinned HuggingFace model has flipped to gated or access-restricted access, and when one has.
How it runs
The automated pipeline, trigger to output.
- TriggerHourly schedule triggers check
- ActionQuery gated status for each pinned modelHugging Face
- LogicBranch if a model flipped open to gated
- ActionCompose issue body with affected services
- OutputOpen high-severity GitLab issue to on-callGitLab
What it does
Detects when a previously open HuggingFace model becomes gated (requires accepting terms or requesting access). A gating flip silently breaks CI and inference the moment your cached weights expire, so this agent surfaces it as an actionable GitLab issue the instant it happens.
When to use it
Use it if your pipelines download model weights at build or deploy time and a sudden access wall would cause outages. Best for platform teams who would rather get a tracked issue today than a failed deploy at 2am.
How it works
- 1An hourly schedule triggers the check.
- 2Query each pinned model's repo settings on HuggingFace for its `gated` status.
- 3Branch: if a model that was open is now gated (or its gate type changed), continue; otherwise exit quietly.
- 4Build an issue body listing the affected model, its new gate type, and the dependent services.
- 5Open a GitLab issue tagged `severity::high` and `model-access`, assigned to the platform on-call.
Set it up
What you configure once, before turning it on.
- 1Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 2Connect GitLabRepos, MRs, pipelines, registry.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Datadog Bill Spike Attribution Agent
When a daily Datadog cost check detects a spend jump, an agent attributes the increase to the specific services and metric types driving it and posts a ranked breakdown to Slack.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
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.