AI AGENTS
Vercel function-invocation cost spike attributor
When a Vercel usage webhook signals a spend or invocation spike, an agent attributes the cost to the specific serverless or edge route driving it.
How it runs
The automated pipeline, trigger to output.
- TriggerVercel usage-alert webhookVercel
- ActionFetch per-function invocations and duration (Vercel API)Vercel
- LogicClassify cause: traffic vs duration vs cache regression
- ActionDraft root cause and remediationOpenAI
- OutputCreate Linear ticket scoped to the offending routeLinear
What it does
Turns a Vercel usage spike into an accountable engineering task. It maps the extra spend to the exact function route, distinguishes a traffic increase from a per-request regression (slower duration or no caching), and opens a Linear ticket scoped to that route.
When to use it
When Vercel function invocations or compute costs jump and you need to know which API route or page handler is responsible before the next billing cycle compounds it.
How it works
- 1A Vercel usage-alert webhook fires when spend or invocations cross a configured limit.
- 2The agent queries the Vercel REST API for per-function invocation counts, average duration, and edge vs node execution over the spike window.
- 3A logic step classifies the cause: more traffic, longer duration, or a cache-control regression on a previously cached route.
- 4An OpenAI step writes a root-cause summary and a concrete remediation (add s-maxage, memoize, or move to edge).
- 5A Linear issue is created on the owning team's project, titled with the route and tagged cost-regression.
Set it up
What you configure once, before turning it on.
- 1Connect VercelDeploys, runtime logs, analytics.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect LinearIssues, projects, cycles, triage.
- 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.