SUMMARIZATION
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.
How it runs
The automated pipeline, trigger to output.
- TriggerSentry release createdSentry
- ActionFetch issues that regressed in the release windowSentry
- LogicStop if no regressions found
- ActionSummarize each regressed issueOpenAI
- OutputOpen a grouped regression ticketLinear
What it does
This workflow watches for one specific failure mode: an error class that was previously resolved and has now come back in a new release. It gathers every regressed Sentry issue tied to the deploy, writes a tight summary of each (what it is, when it was last fixed, how many events since the deploy), and files one Linear ticket grouping them all with direct Sentry links.
When to use it
Use it when regressions keep slipping through because resolved issues stop getting attention. Brand-new errors usually get noticed; quietly reopened ones do not. This guarantees a tracked work item the moment a fix is undone.
How it works
A Sentry release-created event triggers the flow with the new version. The flow queries Sentry for issues whose status flipped from resolved back to unresolved within the release window. A filter drops the run entirely if there are zero regressions, so no empty tickets are created. An OpenAI step writes a per-issue summary and a one-line headline. A Linear ticket is created with the headline as the title and the summaries as the body, labeled as a regression.
Set it up
What you configure once, before turning it on.
- 1Connect SentryErrors, performance, releases.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect LinearIssues, projects, cycles, triage.
- 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
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.
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.
Summarize the Zoom webinar Q&A and email follow-ups to attendees
After a Zoom webinar ends, extracts every question asked and its answer, builds a clean Q&A recap with timestamped jump links, and emails it to all registered attendees via Gmail.
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.