AI AGENTS
On-demand cost-spike investigator in Slack
An engineer types a time window in Slack and an agent investigates the Cloudflare and Vercel cost driver for that window on demand, returning the top offending route or asset.
How it runs
The automated pipeline, trigger to output.
- TriggerSlack command with time windowSlack
- ActionQuery Cloudflare top URLs + cache status for windowCloudflare
- ActionQuery Vercel usage for the same windowVercel
- LogicPick larger overage platform and top offender
- ActionExplain driver and write cache ruleOpenAI
- OutputReply in Slack thread with fixSlack
What it does
Gives engineers a chat command to root-cause a cost spike on demand. Instead of waiting for a scheduled report, someone asks about a specific window in Slack and gets back the single biggest cost-driving route or asset across Cloudflare and Vercel, with a ready-to-paste cache rule.
When to use it
When you notice a bill anomaly mid-day and want an immediate, conversational investigation scoped to the exact hours in question, without leaving Slack or opening a dashboard.
How it works
- 1A Slack slash command or mention triggers the workflow with a time window argument.
- 2The agent queries Cloudflare analytics for top URLs and cache status in that window.
- 3It queries Vercel usage for the same window to catch function-side cost.
- 4A logic step picks whichever platform contributed the larger overage and selects the top offender.
- 5An OpenAI step explains the driver and writes a copy-paste cache rule or header fix.
- 6The answer is posted back as a threaded Slack reply on the original request.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect CloudflareWorkers, Pages, R2, KV — the edge stack.
- 3Connect VercelDeploys, runtime logs, analytics.
- 4Connect OpenAIModels, embeddings, files.
- 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 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.