DEVOPS
AI-triage failed Vercel Lighthouse audits into actionable GitLab issues
When a Vercel preview fails its Lighthouse QA gate, an LLM reads the raw audit JSON, summarizes the top fixable problems with concrete remediation steps.
How it runs
The automated pipeline, trigger to output.
- TriggerVercel preview deployment readyVercel
- ActionRun Lighthouse, capture full JSONShell
- LogicContinue only if score below threshold
- ActionLLM ranks and explains fixesOpenAI
- ActionOpen labeled GitLab issue with planGitLab
- OutputComment issue link on the MRGitLab
What it does
Turns a noisy failed Lighthouse report into a prioritized, human-readable action plan. The LLM ranks opportunities by estimated impact, explains the likely cause, and suggests a fix for each, then files it as a structured GitLab issue tied back to the MR.
When to use it
Use it when raw Lighthouse output overwhelms authors and failures get ignored. Best for teams that want the gate to produce work that is immediately ready to pick up, not a wall of metrics.
How it works
- 1A Vercel deployment-ready webhook provides the preview URL and MR reference.
- 2A shell step runs Lighthouse and captures the full audit JSON.
- 3A logic branch proceeds only when the overall score is below the gate threshold.
- 4An OpenAI step summarizes the worst opportunities into ranked, fix-oriented recommendations.
- 5A GitLab action opens a labeled issue with the recommendations, linked to the MR.
- 6The MR receives a comment linking to the new triage issue.
Set it up
What you configure once, before turning it on.
- 1Connect VercelDeploys, runtime logs, analytics.
- 2Connect ShellRun sandboxed commands inside the workspace.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect GitLabRepos, MRs, pipelines, registry.
- 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 DevOps workflows
Slack-approved pause for idle Hugging Face Spaces
On a daily scan it finds idle paid Spaces and posts an interactive Slack approval; on approve it pauses the Space and logs the decision to a GitHub issue audit trail.
Block costly Hugging Face Space hardware upgrades in PR review
When a pull request changes a Space's hardware config, it estimates the new monthly cost and posts a GitHub PR comment that flags upgrades crossing a budget ceiling.
Hugging Face Spaces idle-runtime sweep with auto-pause
On a schedule, scans all Hugging Face Spaces for ones running idle past a threshold, pauses them to stop billing, and posts a Slack summary with the estimated monthly savings.
Open a Zoom war-room from a Datadog multi-alert storm
When a Datadog monitor crosses a critical threshold, this workflow dedupes against active incidents, and only for a genuinely new outage it creates a Zoom bridge.
Auto-spin a Zoom war-room when PagerDuty hits SEV-1
When a PagerDuty incident escalates to a critical severity, this workflow creates a dedicated Zoom meeting and posts the bridge link to the incident's Slack channel so responders…
Spin up a war-room on demand from a Slack slash command
When an engineer runs a Slack command, this workflow creates a Zoom bridge, opens a tracking Sentry-linked incident, files a Linear issue for follow-up.
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.