SUMMARIZATION
Sentry error spike to deduplicated Linear issue
When Sentry alerts on an error spike, clusters the related error groups by root cause and opens a single Linear issue with a plain-English summary.
How it runs
The automated pipeline, trigger to output.
- TriggerSentry metric alert webhookSentry
- ActionFetch contributing error groups and tracesSentry
- LogicCluster groups by root-cause signature
- ActionSearch Linear for existing issue by signatureLinear
- ActionWrite plain-English regression summaryOpenAI
- LogicBranch: comment on match or create new
- OutputCreate or update Linear issueLinear
What it does
Converts a Sentry spike alert into exactly one well-written Linear issue instead of a pile of duplicate tickets. It pulls the error groups behind the spike, clusters them by root-cause signature, summarizes the failure in plain English, and either creates a new Linear issue or comments on the existing one for that root cause.
When to use it
When on-call keeps filing near-identical bugs for the same underlying break, or when alert noise turns into ticket noise. Use it to keep one canonical issue per root cause with a human-readable description.
How it works
- 1A Sentry metric-alert webhook fires when an error rate crosses threshold.
- 2Fetch the contributing error groups and their stack traces from Sentry.
- 3Cluster them by root-cause signature to find the single underlying cause.
- 4Search Linear for an open issue already tagged with that signature.
- 5An LLM writes a regression summary with impact, first-seen, and suspect commit.
- 6If a match exists, comment with the update; otherwise create a new Linear issue.
Set it up
What you configure once, before turning it on.
- 1Connect SentryErrors, performance, releases.
- 2Connect LinearIssues, projects, cycles, triage.
- 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 Summarization workflows
On-submit Loom standup roll-up archived to Confluence
When a standup video is submitted via webhook, transcribes it, generates a per-person written summary, and appends it to a running team standup page in Confluence.
Front Escalation Handoff Doc in Notion
When a Front escalation closes, drafts a structured handoff document in Notion capturing the resolution, customer commitments, and open follow-ups, then alerts the AE in Slack.
Front Escalation War-Room Brief to Slack
On a Front escalation, posts a concise threat-assessment brief to a Slack channel only when the AI judges the situation high-severity.
VIP Front Escalation Instant Exec Page-Out
Detects escalations from VIP accounts in Front, generates a one-paragraph executive recap, and pages the named account exec via Slack and Salesforce task within minutes.
Release health note per Vercel deploy
When a Vercel deploy goes live, summarizes the Sentry errors observed in the release window into a plain-English health note that separates brand-new error classes…
Rollback recommendation when a deploy spikes errors
When a Sentry alert fires for an error spike, attributes it to the most recent deploy, summarizes whether the spike is dominated by new error classes introduced by that release.
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.