AI AGENTS
New Error Pattern to Linear Triage
When Axiom detects a log pattern that never appeared before a deploy, an agent decides if it is a real regression and, when it is, files a deduplicated Linear issue with sample…
How it runs
The automated pipeline, trigger to output.
- TriggerAxiom monitor on new error patternAxiom
- ActionFetch sample events and trendAxiom
- ActionLLM classifies regression vs noiseOpenAI
- LogicDedupe against open Linear issuesLinear
- OutputFile or comment Linear issue and ping SlackSlack
What it does
This agent watches for genuinely new error-shaped log patterns that surface right after a deploy. For each one it decides whether it looks like a real regression worth tracking, and if so opens a Linear issue with representative samples, frequency, and the deploy commit that likely introduced it. It dedupes against open issues so the same pattern never files twice.
When to use it
Use it when new errors slip through because they are low-volume at first and only get noticed once they spike. This catches the first occurrence and routes it to the team's tracker with enough context to act.
How it works
- 1An Axiom monitor fires when a previously unseen error template crosses a small occurrence threshold.
- 2The agent pulls sample events and the count trend for that pattern.
- 3An LLM step classifies it as regression, transient, or expected noise, and drafts a title and description.
- 4A logic step checks Linear for an existing issue matching the pattern fingerprint and skips if found.
- 5It creates or comments on a Linear issue, then notifies the owning team in Slack.
Set it up
What you configure once, before turning it on.
- 1Connect AxiomLog streams, queries, dashboards.
- 2Connect LinearIssues, projects, cycles, triage.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Connect OpenAIModels, embeddings, files.
- 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 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.
