AI AGENTS
AI License-Risk Triage Agent for HuggingFace Model Changes
When a pinned HuggingFace model's license text changes, an LLM classifies the new license against your usage policy (commercial, redistribution.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule starts run
- ActionFetch current license text per pinned modelHugging Face
- LogicDetect models with changed license body
- ActionLLM classifies permitted uses and risk tierOpenAI
- OutputOpen GitLab MR labeled by risk with rationaleGitLab
What it does
Goes beyond matching a license string: when a model's full license text changes, an LLM reads the new terms and classifies them against your company's usage policy, deciding whether commercial use, redistribution, and fine-tuning remain permitted. It then opens a GitLab MR carrying a risk tier and a human-readable explanation so reviewers don't have to read legalese from scratch.
When to use it
Use it when models you depend on ship novel or custom licenses that a simple allowlist can't evaluate, and you want a first-pass legal read attached to every change before a human reviews it.
How it works
- 1A daily schedule starts the run.
- 2Fetch each pinned model's current license text and terms from HuggingFace.
- 3Detect which models have a changed license body since the last run.
- 4Send the new terms to an LLM to classify permitted uses and assign a low/medium/high risk tier with rationale.
- 5Open a GitLab MR per changed model, labeled with the risk tier and the LLM's summary in the description.
Set it up
What you configure once, before turning it on.
- 1Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect GitLabRepos, MRs, pipelines, registry.
- 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 AI Agents workflows
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.
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.
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.
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.
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.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
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.