SUMMARIZATION
Voice Safety Report Coordinator with Trend Tracking
An agent transcribes a crew safety voice report, condenses it into a structured incident record, logs it to a Postgres trend table.
How it runs
The automated pipeline, trigger to output.
- TriggerVoice safety report posted to webhookHTTP webhook
- ActionTranscribe report with ElevenLabsElevenLabs
- ActionCondense into structured incident record
- ActionLog record and read recent trend historyPostgres
- LogicJudge whether pattern crosses threshold
- OutputAlert safety lead in Slack if flaggedSlack
What it does
Processes spoken safety observations from the field into structured records, accumulates them, and reasons over recent history to decide whether a recurring hazard deserves a human's attention right now.
When to use it
For operations where near-misses and hazards are reported verbally and the real risk is a slow-building pattern no single report reveals. Use it when you want both a clean log and judgment about when to escalate.
How it works
- 1A voice safety report uploaded via webhook triggers the agent.
- 2ElevenLabs transcribes the report.
- 3The agent condenses it into a structured record: location, hazard type, severity, and a one-line summary.
- 4It writes the record to a Postgres safety-trend table and reads back recent entries for the same location or hazard type.
- 5The agent decides whether frequency or severity crosses a threshold.
- 6If it does, it posts a flagged trend alert to the safety lead in Slack with the contributing reports; otherwise it logs silently.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect ElevenLabsText-to-speech, voice cloning.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 4Connect SlackChannels, DMs, threads, mentions.
- 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
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.