AI AGENTS
Axiom Ingest Spike → Noisy-Service Triage Agent
When daily Axiom ingestion volume jumps past a threshold, an agent finds the service and log pattern driving the spike and opens a Linear issue with a proposed sampling fix.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule fires the cost check
- ActionQuery Axiom for today's bytes vs 14-day baselineAxiom
- LogicSpike exceeds threshold?
- ActionQuery Axiom grouped by service and message fingerprintAxiom
- ActionAgent identifies noisy service and drafts sampling rule
- OutputOpen Linear issue with culprit and proposed fixLinear
What it does
Watches your Axiom log-ingestion volume day over day. When today's bytes-ingested jumps materially above the trailing baseline, it pinpoints which service and which repeating log pattern caused the increase, then files a Linear issue that names the culprit and proposes a concrete sampling or log-level change to bring volume back down.
When to use it
Use it when your observability bill is creeping up and nobody notices until finance flags it. Best for teams on usage-based log pricing who want the noisy emitter identified automatically instead of manually slicing dashboards after the invoice lands.
How it works
- 1A daily schedule fires the run.
- 2It queries Axiom for total bytes ingested today versus the trailing 14-day median.
- 3A logic gate checks whether the increase clears the configured threshold; if not, the run ends quietly.
- 4On a spike, it queries Axiom again grouped by service and message fingerprint to rank the top contributors.
- 5The agent reasons over the breakdown to identify the single noisy service and the repeating line driving cost.
- 6It opens a Linear issue describing the spike, the offending pattern, and a drafted sampling rule.
Set it up
What you configure once, before turning it on.
- 1Connect AxiomLog streams, queries, dashboards.
- 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.