SUMMARIZATION
Classify Zoom Call Objections with a Hugging Face Model and Log to Coda
Runs each Zoom sales-call transcript through a Hugging Face zero-shot classifier to label objections into a fixed taxonomy, then logs the labeled.
How it runs
The automated pipeline, trigger to output.
- TriggerZoom sales call recording completedZoom
- ActionSegment transcript into objection passagesZoom
- ActionZero-shot classify each passage with Hugging FaceHugging Face
- LogicKeep passages above the confidence threshold
- OutputAppend labeled verbatim objections to Coda tableCoda
What it does
Gives you a consistent, model-backed objection taxonomy instead of free-form summaries. Each Zoom transcript is segmented into objection moments, and a Hugging Face zero-shot classification model assigns every moment to one of your defined labels (budget, timing, integration risk, security, decision authority). The verbatim text, label, and confidence score land in Coda as structured rows.
When to use it
Use when you want analyzable, queryable objection data with stable category labels you can pivot on, and you prefer a dedicated classification model over prompting an LLM for categories. Good for RevOps teams building dashboards on objection frequency.
How it works
- 1A Zoom recording-completed event delivers the finished call.
- 2The transcript is segmented into candidate objection passages with timestamps.
- 3Each passage is sent to a Hugging Face zero-shot classifier against your label set.
- 4A logic step keeps only passages above the confidence floor and attaches the winning label.
- 5Each labeled verbatim objection is appended as a row to the Coda objection-tracking table.
Set it up
What you configure once, before turning it on.
- 1Connect ZoomMeetings, recordings, transcripts.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 3Connect CodaDocs, packs, automations.
- 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.