AI AGENTS
Axiom Ingest Cost-Spike Investigator
When Axiom daily ingest volume jumps past a threshold, an agent pinpoints which datasets and fields drove the spike and posts a ranked breakdown with proposed drop/sampling rules…
How it runs
The automated pipeline, trigger to output.
- TriggerDaily scheduled ingest check
- ActionPull 24h ingest bytes per dataset from AxiomAxiom
- LogicContinue only if ingest exceeds spike threshold
- ActionQuery Axiom for top datasets and noisy fieldsAxiom
- ActionAgent attributes spike and drafts drop/sampling rulesOpenAI
- OutputPost ranked breakdown and proposed rules to SlackSlack
What it does
Watches your Axiom ingest volume and, on a sudden spike, runs an investigation that attributes the extra gigabytes to specific datasets, log sources, and high-cardinality fields. It then drafts concrete drop and sampling rules to bring spend back down and posts the whole brief to your observability Slack channel for a human to approve.
When to use it
Use it when log-ingest cost is a recurring surprise and you want the root cause and a fix proposal waiting for you instead of spending an afternoon slicing dashboards. Good for platform and SRE teams on usage-based observability billing.
How it works
- 1A scheduled check pulls the last 24h of Axiom ingest bytes per dataset and compares against the trailing 7-day baseline.
- 2A logic gate continues only if total ingest exceeds the spike threshold (e.g. +40%).
- 3The agent queries Axiom to rank the top datasets and noisiest fields contributing the delta.
- 4The agent reasons over the breakdown and drafts targeted drop/sampling rule candidates with estimated savings.
- 5The findings and proposed rules are posted to Slack for approval.
Set it up
What you configure once, before turning it on.
- 1Connect AxiomLog streams, queries, dashboards.
- 2Connect SlackChannels, DMs, threads, mentions.
- 3Connect OpenAIModels, embeddings, files.
- 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.