SUMMARIZATION
Sentry Regression Auto-Triage with Rollback Recommendation
On a new deploy, scores the Sentry error-rate jump against the prior release and, when the regression breaches a severity threshold, pages on-call via PagerDuty with a brief…
How it runs
The automated pipeline, trigger to output.
- TriggerVercel deploy succeededVercel
- ActionFetch Sentry error + blast-radius deltasSentry
- LogicScore severity and check page threshold
- ActionSummarize regression + rollback recommendationOpenAI
- OutputPage on-call via PagerDuty incidentPagerDuty
What it does
Acts as a first-pass triage analyst for risky deploys. It compares the live release's Sentry error rate to the release it replaced, scores the regression by magnitude and blast radius (sessions affected), and decides whether the situation warrants paging on-call. The page carries a concise brief and an explicit recommendation: roll back now, or watch closely.
When to use it
Use it when a bad deploy needs a human in minutes, not whenever someone next checks a dashboard. It separates cosmetic error bumps from genuine stability regressions so you only page for the latter.
How it works
- 1A Vercel deployment-succeeded webhook fires.
- 2Fetch Sentry error rate and affected-session counts for the new and prior releases and compute the delta.
- 3Score severity from delta size and user blast radius; branch on whether it clears the page threshold.
- 4If below threshold, end without paging.
- 5Summarize the regression and derive a rollback-or-watch recommendation.
- 6Open a PagerDuty incident carrying the brief to on-call.
Set it up
What you configure once, before turning it on.
- 1Connect VercelDeploys, runtime logs, analytics.
- 2Connect SentryErrors, performance, releases.
- 3Connect PagerDutyIncidents, on-call, escalations.
- 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 Summarization workflows
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…
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.
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.
Escalate blockers from Loom standups to Slack
Transcribes each new Loom standup video, uses AI to detect blockers and dependencies.
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.