DEVOPS
Axiom Budget Triage Agent
An agent investigates a projected Axiom overage end to end — diagnoses the noisy source, decides whether to auto-throttle via Cloudflare or escalate to a Linear ticket.
How it runs
The automated pipeline, trigger to output.
- TriggerEvery 2 hours with current projection
- ActionAgent investigates top Axiom sourcesAxiom
- LogicAgent decides throttle vs. escalate
- ActionThrottle source via Cloudflare samplingCloudflare
- ActionOr open Linear ticket for reviewLinear
- OutputPost rationale and action to SlackSlack
What it does
Instead of a fixed rule, this agent triages a projected Axiom overage like an engineer would. It investigates which source is driving spend, judges whether the spike is a safe-to-throttle nuisance (verbose debug logs, health-check chatter) or a real signal that needs human review, then either tightens Cloudflare sampling or files a Linear ticket — and explains why.
When to use it
Use it when overage causes are varied enough that a single deterministic rule misfires. The agent's judgment handles the gray-area cases: throttle the obviously noisy, escalate the ambiguous.
How it works
- 1A schedule fires every 2 hours and hands the agent the current Axiom projection.
- 2The agent queries Axiom to identify and characterize the top contributing sources.
- 3It reasons over whether each top source is safe to throttle or needs human eyes.
- 4Decision branch: auto-throttle the source via Cloudflare sampling, or open a Linear ticket for review.
- 5Execute the chosen action.
- 6Post a written rationale and the action taken to Slack.
Set it up
What you configure once, before turning it on.
- 1Connect AxiomLog streams, queries, dashboards.
- 2Connect CloudflareWorkers, Pages, R2, KV — the edge stack.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Connect SlackChannels, DMs, threads, mentions.
- 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 DevOps workflows
Slack-approved pause for idle Hugging Face Spaces
On a daily scan it finds idle paid Spaces and posts an interactive Slack approval; on approve it pauses the Space and logs the decision to a GitHub issue audit trail.
Block costly Hugging Face Space hardware upgrades in PR review
When a pull request changes a Space's hardware config, it estimates the new monthly cost and posts a GitHub PR comment that flags upgrades crossing a budget ceiling.
Hugging Face Spaces idle-runtime sweep with auto-pause
On a schedule, scans all Hugging Face Spaces for ones running idle past a threshold, pauses them to stop billing, and posts a Slack summary with the estimated monthly savings.
Open a Zoom war-room from a Datadog multi-alert storm
When a Datadog monitor crosses a critical threshold, this workflow dedupes against active incidents, and only for a genuinely new outage it creates a Zoom bridge.
Auto-spin a Zoom war-room when PagerDuty hits SEV-1
When a PagerDuty incident escalates to a critical severity, this workflow creates a dedicated Zoom meeting and posts the bridge link to the incident's Slack channel so responders…
Spin up a war-room on demand from a Slack slash command
When an engineer runs a Slack command, this workflow creates a Zoom bridge, opens a tracking Sentry-linked incident, files a Linear issue for follow-up.
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.