AI AGENTS
Cloudflare Cache-Hit Optimizer Agent
An agent reads Cloudflare edge analytics on a schedule, finds the URL patterns bleeding cache misses, and drafts specific page-rule and cache-key changes for review in Linear.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionPull zone cache analytics and per-path hit/missCloudflare
- LogicAgent diagnoses miss causes per URL pattern
- LogicFilter to patterns above miss-rate threshold
- ActionDraft page-rule / cache-key proposals
- OutputOpen a Linear issue per proposal for approvalLinear
What it does
This agent inspects your Cloudflare zone's edge analytics, identifies the request patterns dragging down your cache-hit ratio, and proposes concrete remediations — a page rule to extend Edge Cache TTL, a cache-key rewrite to strip noisy query params, or an origin Cache-Control fix. Each proposal lands as a Linear issue with the evidence attached, so nothing changes in production without a human approving it.
When to use it
Run it when your bandwidth bill or origin load is climbing and you suspect cacheable content is slipping through. Good for teams who want a standing weekly review of cache health rather than a one-off audit.
How it works
- 1A weekly schedule wakes the agent.
- 2It pulls the zone's cache analytics and per-path hit/miss breakdown from Cloudflare.
- 3It reasons over the data: which paths are MISS-heavy, whether the cause is short TTL, query-string fragmentation, or a no-cache origin header.
- 4A branch checks whether any pattern crosses the configured miss-rate threshold; below it, the run ends quietly.
- 5For each qualifying pattern it drafts a specific page-rule or cache-key change with before/after reasoning.
- 6It opens a Linear issue per proposal, tagged for the platform team to approve and apply.
Set it up
What you configure once, before turning it on.
- 1Connect CloudflareWorkers, Pages, R2, KV — the edge stack.
- 2Connect LinearIssues, projects, cycles, triage.
- 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
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.