SUMMARIZATION
Route brand-new error classes by severity after release
Identifies error classes that appear for the first time in a release, has an LLM judge their severity from the stack trace and event volume.
How it runs
The automated pipeline, trigger to output.
- TriggerVercel deployment succeeded webhookVercel
- ActionFetch first-seen Sentry issues in the windowSentry
- ActionSummarize and severity-score each new classOpenAI
- LogicBranch on assigned severity
- OutputPage on-call for high severityPagerDuty
- OutputFile backlog ticket for the restLinear
What it does
This workflow isolates the truly new errors a release introduced (issues with no history before the deploy), then triages them. An LLM reads each new issue's message, stack trace, and event rate and assigns a severity. High-severity issues escalate to PagerDuty; everything else becomes a Linear backlog item. The decision is explained in plain English so the routing is auditable.
When to use it
Use it when a deploy can introduce both a five-alarm fire and harmless new log noise, and you want the fire to page someone while the noise just gets queued. It keeps on-call alerts meaningful without ignoring the long tail.
How it works
A Vercel deploy-succeeded webhook supplies the release. The flow fetches Sentry issues first-seen inside the window. An OpenAI step summarizes and severity-scores each new class. A branch splits on the assigned severity: high-severity issues trigger a PagerDuty incident with the summary as context, while medium and low issues are written to Linear as backlog tickets.
Set it up
What you configure once, before turning it on.
- 1Connect VercelDeploys, runtime logs, analytics.
- 2Connect SentryErrors, performance, releases.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect PagerDutyIncidents, on-call, escalations.
- 5Connect LinearIssues, projects, cycles, triage.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Summarization workflows
Daily Front Escalation Digest with Salesforce Rollup
Each morning, sweeps the prior day's escalated Front conversations, summarizes each, enriches with Salesforce account value, and emails account execs a single prioritized digest.
File a Linear ticket for regressed errors after deploy
Detects Sentry issues that regressed in the latest deploy's release window, summarizes what broke and when it was previously fixed.
Daily release-health rollup to Confluence
Each morning, compares the last 24 hours of Sentry activity against the deploys that shipped in that window and publishes a dated release-health page to Confluence summarizing…
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.
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.
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.