SUMMARIZATION
Route discovery-call feature requests into deduplicated Linear issues
When a Zoom discovery call ends, extracts each feature request from the transcript, checks it against existing Linear issues.
How it runs
The automated pipeline, trigger to output.
- TriggerZoom discovery call endsZoom
- ActionExtract feature requests + quotes from transcriptOpenAI
- ActionSearch Linear for similar open issuesLinear
- LogicBranch: existing match vs net-new request
- OutputAppend evidence or file new triaged Linear issueLinear
What it does
Closes the loop between what customers ask for on calls and what product actually tracks. As soon as a discovery call wraps, it reads the transcript, pulls out concrete feature requests, and reconciles each one against your Linear backlog. If a matching issue already exists, it appends the new customer quote and bumps the demand count. If nothing matches, it opens a new issue with the request, the verbatim quote, and the account name.
When to use it
Use this when good feature signal dies in call recordings because no one transcribes it into the tracker, or when the same request gets filed five times under five names. It keeps Linear as the single source of customer demand without manual triage after every call.
How it works
- 1A Zoom call-ended event triggers the workflow for recordings tagged as discovery.
- 2OpenAI extracts a list of discrete feature requests with a one-line summary and supporting quote each.
- 3For each request, the workflow searches Linear for semantically similar open issues.
- 4A branch decides: match found versus net-new request.
- 5Matches get the quote appended and a demand counter incremented; net-new requests become triaged Linear issues with account context.
Set it up
What you configure once, before turning it on.
- 1Connect ZoomMeetings, recordings, transcripts.
- 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.