# Turn Otter.ai customer calls into a Notion product feedback board

> When a customer call finishes in Otter, an agent pulls out feature requests and pain points, then files them into your Notion feedback database by theme instead of creating duplicates.

- Workflow type: agent
- Services: Otter.ai, Notion
- Categories: Product, Customer Support
- Published: 2026-07-02

## What it does

- Listens for finished Otter.ai conversations and skips anything that isn't customer-facing, like internal syncs, hiring interviews, and prospect-only meetings without product talk.
- Reads the transcript for real product signal: feature requests, pain points, workarounds, and competitor mentions, each captured with a short verbatim quote.
- Checks your Notion feedback database for an existing page on the same theme and appends fresh evidence to it, so themes accumulate over time instead of fragmenting into dozens of one-off pages.
- Creates a new theme page only when nothing matches, filling in customer, sentiment, call date, and a link back to the Otter conversation.

## What you'll need

- An Otter.ai Enterprise workspace with Public API access turned on by your account manager.
- A Notion workspace and a feedback database shared with your General Input connection.
- A short list of properties on that database, such as Theme, Customer, Sentiment, Call date, and Source link.

## Prompt

Build an agent workflow that turns finished Otter.ai calls into product feedback entries in Notion, deduplicated by theme.

Trigger: an Otter.ai workspace webhook on the conversation.completed event. The agent should run once per finished conversation and receive the conversation id, title, host, participants, and summary from the webhook payload. If the agent needs more context (full transcript or metadata), it can call Otter's List Workspace Conversations to pull recent items or read details from the completed conversation.

Step 1: classify the call. The agent decides whether this is customer-facing product signal. Customer-facing means discovery, onboarding, support, or CS check-in calls with an external customer or prospect who is actively discussing our product. Explicitly skip: internal team syncs, hiring interviews, vendor pitches, and calls that never mention product feedback. If the call is not customer-facing, stop and do nothing.

Step 2: extract product signal. From the transcript and summary, pull out feature requests, pain points, workarounds, and competitor mentions. For each item, capture a short verbatim quote, a one-line paraphrase, and a theme (e.g. pricing, onboarding, reporting, mobile, integrations, reliability). Also infer sentiment (positive, neutral, negative, blocking) and note the customer name and call date.

Step 3: dedupe by theme against Notion. The user will point the agent at a Notion feedback database (data source id). For every extracted item, call Notion's Query a Data Source to look for an existing page on the same theme (match on the Theme property and, when helpful, on the paraphrased description). Pick the best match; if nothing matches, treat it as new.

Step 4a: if a matching theme page exists, use Append Block Children on that page to add a new bulleted list item containing: the verbatim quote, the customer name, the call date, and a link back to the Otter conversation. Also add a short note about sentiment. Do not create a new page.

Step 4b: if no matching theme page exists, use Create a Page as a child of the feedback data source. Set properties for Theme, Customer, Sentiment, Call date, and Source link (link back to the Otter conversation). In the page body, add the verbatim quote, the paraphrased summary, and a bullet list started with the first evidence entry so future calls can append to it in the same shape as step 4a.

Behavior rules the agent should follow: never file the same call's evidence twice on the same page. If the customer or call date is missing, use best-effort values from the Otter conversation metadata. Prefer appending to an existing theme page over creating a new one when the match is reasonable. Keep verbatim quotes short (one or two sentences). Always include the Otter conversation link so anyone reading the board can jump back to context.

Setup inputs the workflow should ask the user for on first run: the Notion feedback database (data source id), the exact property names for Theme, Customer, Sentiment, Call date, and Source link, and any custom rules for what counts as customer-facing (for example, include partner calls, exclude a specific channel).

## How to customize

- Change what counts as customer-facing (for example, include partner calls or exclude support tickets logged as calls).
- Tune the theme categories the agent looks for, such as pricing, onboarding, integrations, or reliability.
- Adjust which properties get filled on a new page, or add tags like product area and account tier.

## FAQ

### Will this create duplicate pages if two calls raise the same issue?

No. Before creating anything, the agent searches your feedback database for a page that already covers the same theme and appends a new bullet with the quote and call link. A new page is only created when nothing matches.

### What happens with internal meetings or hiring interviews?

The agent classifies the call first and skips anything that isn't customer-facing. Internal syncs, hiring loops, and vendor pitches are ignored so your feedback board stays clean.

### Does this work on any Otter.ai plan?

You need an Enterprise workspace with Public API access enabled. Otter grants that on request through your account manager. Team and Business plans do not currently expose the webhook.

### Do I have to structure my Notion database a specific way?

No, but the agent works best when your database has properties for Theme, Customer, Sentiment, Call date, and a link back to the source call. You can rename or add fields and tell the agent about them when you set it up.

### Can I run it on past calls instead of only new ones?

Yes. Ask the agent to backfill and it will pull recent workspace conversations and process the customer-facing ones in the same way.

Use this prompt in General Input: https://www.generalinput.com/prompts/turn-otterai-customer-calls-into-a-notion-product-feedback-board