DEVOPS
Agent-written cache-regression RCA from Cloudflare, Vercel and Datadog
When an origin-load spike is detected, an agent gathers Cloudflare cache data, the suspect Vercel deploy diff, and Datadog signals.
How it runs
The automated pipeline, trigger to output.
- TriggerOrigin-load-spike webhookHTTP webhook
- ActionPull Cloudflare cache-status detailCloudflare
- ActionFetch suspect Vercel deploy + changesVercel
- ActionQuery Datadog for correlated signalsDatadog
- LogicAgent synthesizes root-cause narrative
- OutputWrite RCA draft to Notion incident pageNotion
What it does
This workflow has an agent investigate a cache regression and write it up. Triggered by a detected origin-load spike, it gathers the Cloudflare cache-status breakdown, the suspect Vercel deploy and its changes, and correlated Datadog metrics, then reasons over the evidence to draft a structured root-cause analysis: what regressed, the likely cause, and recommended remediation. The draft lands in Notion for an engineer to confirm.
When to use it
Use it when you want a human-readable RCA started automatically while context is fresh, instead of reconstructing a timeline hours later. It fits teams who keep incident records in Notion and want the tedious evidence-gathering and first draft done for them.
How it works
- 1An origin-load-spike webhook fires from your detection layer.
- 2The agent pulls the Cloudflare cache-status and cache-hit ratio detail for the affected zone.
- 3It fetches the suspect Vercel deploy and its change summary.
- 4It queries Datadog for correlated latency and error signals around the spike.
- 5The agent synthesizes a root-cause narrative with timeline, cause, and remediation.
- 6It writes the RCA draft to a Notion incident page for human review.
Set it up
What you configure once, before turning it on.
- 1Connect CloudflareWorkers, Pages, R2, KV — the edge stack.
- 2Connect VercelDeploys, runtime logs, analytics.
- 3Connect DatadogMetrics, traces, log search.
- 4Connect NotionPages, databases, comments.
- 5Connect HTTP webhookTrigger any URL on agent actions.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More DevOps workflows
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.
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.
Generate a weekly de-flake report and assign Linear cleanup tickets
On a weekly schedule, aggregates the current quarantine manifest and recent flake history, builds a prioritized report.
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.
Auto-release tests from quarantine once they prove stable
Triggered by a webhook from a nightly stability runner, checks whether quarantined tests have passed enough consecutive runs, removes the stable ones from quarantine in GitHub.
Quarantine a test on demand from a PR comment command
Triggered when an engineer comments a quarantine command on a pull request, validates the test name, commits the quarantine change to that PR branch, opens a tracking issue.
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.