AI AGENTS
Axiom Runaway-Ingest Auto-Sampling Guard
On a severe Axiom ingest spike, an agent confirms a true runaway logger, applies an emergency sampling rule to cap the bleeding.
How it runs
The automated pipeline, trigger to output.
- TriggerAxiom severe ingest-rate webhookHTTP webhook
- ActionConfirm offending dataset and rule out traffic surgeAxiom
- LogicProceed only if runaway-logger pattern confirmed
- ActionApply scoped emergency sampling rule via AxiomAxiom
- OutputPage on-call with action and revert stepsPagerDuty
What it does
Acts as a fast guardrail against runaway loggers that can burn a month of budget in hours. On a severe spike the agent verifies the pattern is a genuine flood (not a legitimate traffic surge), applies a pre-scoped emergency sampling rule to the offending dataset to cap ingest, then pages on-call with a clear record of the action and the option to revert.
When to use it
Use it when a single bad deploy or log loop can rack up serious cost before a human notices. The automatic cap buys time; on-call stays in control via the page and can roll back immediately.
How it works
- 1An Axiom monitor webhook fires on a severe ingest-rate breach.
- 2The agent queries Axiom to confirm a single dataset/field is responsible and rules out a broad traffic surge.
- 3A logic gate proceeds only if the runaway-logger pattern is confirmed.
- 4The agent applies a scoped emergency sampling rule via the Axiom API to cap ingest.
- 5PagerDuty is triggered for on-call with the action taken, the evidence, and revert instructions.
Set it up
What you configure once, before turning it on.
- 1Connect AxiomLog streams, queries, dashboards.
- 2Connect PagerDutyIncidents, on-call, escalations.
- 3Connect HTTP webhookTrigger any URL on agent actions.
- 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.