# Review every ElevenLabs voice agent call with a QA scorecard

> Open one queue each morning, score every voice agent call against your rubric, and let an assistant pre-fill each scorecard before you approve it.

- Workflow type: app
- Services: ElevenLabs, Google Sheets, Slack Bot, HubSpot
- Categories: Customer Support, Operations
- Published: 2026-08-24

## What it does

- Lists every recent call your voice agents handled in one review queue, showing the agent name, how long the call ran, who was on the line, and whether anyone has scored it yet
- Puts the full transcript next to an inline audio player so you can read and listen to the same moment without leaving the page
- Scores each call against a fixed five point rubric covering the greeting, identity check, required disclosure, whether the question was actually answered, and whether the caller got a clear next step
- Kicks off an assistant that reads the transcript, suggests a pass or fail on every rubric line with the exact quote backing it up, and drafts the follow up wording so reviewers edit instead of starting from a blank form
- Files approved reviews to your spreadsheet log, posts failed calls to a Slack channel, and writes a summary and follow up task onto the caller's CRM record
- Tracks pass rate per agent per week so coaching conversations have history behind them

## What you'll need

- An ElevenLabs account with voice agents that have handled calls
- A Google account with a spreadsheet to use as your QA log
- A Slack workspace where the app can post failed calls to a review channel
- A HubSpot login, so summaries and follow up tasks land on the right contact
- Your QA rubric, if you want to change the five default lines

## Prompt

Build me an app my support QA lead opens every morning to review the calls our ElevenLabs voice agents handled. The whole point is that a reviewer works through a queue of calls, scores each one against a fixed rubric, and signs off, with an assistant doing the first pass so nobody starts from a blank form.

The main view is a review queue. Use the ElevenLabs List Conversational AI Agents operation to get our agents, then List Conversations to pull recent calls across them. Each row shows the agent name, the call duration, the caller, and whether the call has been reviewed yet. Hide any call shorter than thirty seconds so accidental hangups do not clog the queue, and make that cutoff a setting rather than a hardcoded number. Let the reviewer filter by agent and by reviewed or unreviewed.

Selecting a row opens a detail pane. Fetch the full transcript with Get Conversation and show it turn by turn beside an inline audio player fed by Get Conversation Audio, so the reviewer can read and listen to the same moment. Keep the transcript and the player side by side rather than stacked, and make transcript lines clickable references the scorecard can quote.

Every call gets a scorecard against a fixed five line rubric: greeting, identity check, required disclosure, question actually answered, and clear next step. Each line takes a pass or fail plus a free text note. The scorecard also has a space for the drafted follow up wording. Store scorecards in the app's own storage so they persist across sessions and survive the original call being redacted upstream.

Add a "Review this call" button that kicks off a background agent. The agent reads the transcript for that conversation, pre-fills the scorecard with a suggested pass or fail on every rubric line, and quotes the exact transcript lines as evidence for each verdict. It should explicitly flag missed disclosures and questions the agent never actually answered, and draft the follow up wording. Its output lands back in the app as a draft scorecard the reviewer edits and approves. Nothing the agent produces is final on its own. Also add a "Sweep the backlog" button that runs the same agent across every unreviewed call currently in the queue, so a reviewer can arrive to pre-filled scorecards.

Approving a scorecard is the only thing that sends data anywhere. On approve, append a row to our Google Sheets QA log using Append Values, with the call id, agent name, caller, date, each rubric line's verdict and note, the overall pass or fail, and the reviewer's name. If the call failed, post it into a Slack review channel with the Slack Bot Send a Message operation, including which rubric lines failed and the supporting quotes. Then look the caller up in HubSpot with Search Contacts, and on the matching contact write a summary with Create Note plus a Create Task carrying the follow up wording and a due date. If Search Contacts finds no match, say so in the app and still write the spreadsheet row rather than failing the whole save.

Make it multi reviewer. Each reviewer sees their own queue of calls nobody has scored yet, and the name of whoever approves a scorecard is stamped on it and carried into the spreadsheet row, the Slack post, and the CRM note. A call another reviewer already signed off should drop out of my unreviewed queue.

Finally, add a trends tab showing pass rate per agent per week, built from the stored scorecards, so coaching conversations have history behind them. Show the per rubric line failure breakdown too, so it is obvious whether an agent keeps missing the disclosure specifically or is weak everywhere.

One important nuance: ElevenLabs conversation history can be redacted or retention limited depending on plan settings, so treat the Google Sheets log and the app's stored scorecards as the durable record of scores rather than assuming transcripts stay fetchable forever. Never make the trends tab depend on re-fetching old conversations.

## How to customize

- Change the rubric lines to match your own quality standards, or add lines for tone, compliance language, or upsell attempts
- Adjust the minimum call length so very short hangups stay out of the queue, or drop the filter entirely
- Pick which Slack channel gets failed calls, and whether every failure posts or only certain agents
- Decide what the assistant drafts for you, from the follow up wording to the tone of the summary note

## FAQ

### Do reviews get sent anywhere before I approve them?

No. Nothing reaches Slack or your CRM until a person hits approve. The assistant only fills in a suggestion, and the reviewer edits it, signs off, and then the app files everything.

### Can more than one person review calls at the same time?

Yes. Each reviewer sees their own queue of calls nobody has scored yet, and their name gets stamped on every scorecard they sign off, so you always know who reviewed what.

### What happens to very short calls and hangups?

Calls shorter than thirty seconds are hidden by default so accidental hangups do not clog the queue. You can change that cutoff or turn it off if you want to see everything.

### What if I have a backlog of calls nobody has looked at?

There is a sweep the backlog button that runs the assistant across every unreviewed call in the queue at once, so you arrive to pre-filled scorecards instead of an empty list.

### Will my transcripts still be there months from now?

Not always. Voice platforms can redact or age out conversation history depending on your plan settings, which is why every approved score is written to your spreadsheet log. That log is the durable record, not the original call.

### Can I see whether an agent is improving over time?

Yes. The trends tab shows pass rate per agent per week, so you can point at real history in a coaching conversation instead of going on impressions.

Use this prompt in General Input: https://www.generalinput.com/prompts/review-every-elevenlabs-voice-agent-call-with-a-qa-scorecard