SUMMARIZATION
Turn a customer's slow Honeycomb trace into a non-technical Linear performance ticket
On demand, takes a customer's slow trace, writes both a customer-facing plain-English explanation and an engineer-facing summary.
How it runs
The automated pipeline, trigger to output.
- TriggerSupport operator submits trace ID and customer name
- ActionFetch the trace span waterfall and service breakdownHoneycomb
- LogicIdentify and classify the dominant bottleneck span
- ActionGenerate paired customer-facing and engineer-facing summariesOpenAI
- OutputCreate a labeled Linear performance ticket with both summariesLinear
What it does
Given a slow trace tied to a customer complaint, this workflow produces two summaries from one waterfall: a gentle customer-facing explanation of what happened, and a crisp engineering summary of the bottleneck. It then opens a Linear ticket carrying both, so support can reply and engineering can pick it up without re-investigation.
When to use it
Use it when a slow-request complaint needs to become real work. Instead of a vague 'app was slow for ACME' ticket, the team gets a structured issue with the actual culprit span and a reply the support agent can paste back to the customer.
How it works
- 1A support operator triggers the workflow with the trace ID and the affected customer name.
- 2Honeycomb returns the trace's span waterfall and service breakdown.
- 3A logic step finds the dominant span and labels it (database, downstream API, queue wait, or compute).
- 4OpenAI generates two outputs: a customer-friendly explanation and a technical bottleneck summary.
- 5A Linear issue is created with the technical summary in the body, the customer note in a comment, and a latency label applied.
Set it up
What you configure once, before turning it on.
- 1Connect HoneycombDistributed traces and queries.
- 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
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.