← Back to directory
Personal Productivity Medium to set up AI workflow Repurpose/Transform

Meeting Notes From YouTube To Notion

Source reviewed Updated 2026-07-07

Monitors a YouTube channel for new uploads, transcribes the audio with deAPI, extracts key details via an AI agent.

founders and execsops and IT teams

What it does

You automatically capture new YouTube videos, transcribe them instantly, and extract titles, summaries, action items, decisions, and key topics into a structured Notion page while posting updates to Slack. This entire process runs without you needing to download files or manually review transcripts.

Step by step

  1. Configure the n8n RSS trigger to poll the specific YouTube channel feed URL at regular intervals.
  2. Set up the deAPI node with the API key and map the video URL from the RSS item metadata.
  3. Define the Notion database schema with properties for title, summary, action items, decisions, and topics.
  4. Connect the Slack notification node to post a formatted message containing the new page link.

Where the LLM does the work

  • Craft the system prompt for Anthropic to strictly enforce JSON output structure for reliable parsing.
  • Instruct the model to distinguish between explicit action items and general discussion points in the transcript.
  • Refine the summary generation logic to ensure it captures key decisions without including filler content.

Watch out for

Transcription services may fail on long videos, so add error handling to retry or skip problematic entries.
Notion API limits can block bulk operations, so implement small delays between creating multiple pages if needed.
RSS feeds often delay updates by several minutes, so adjust the trigger interval to balance freshness and load.
JSON parsing errors will break the workflow, so wrap the LLM output in a try-catch block with fallback logic.

Tools that fit

n8n Service Workflow orchestration and trigger monitoring
deAPI API Video transcription from YouTube URL
Anthropic Chat Model LLM AI analysis and extraction of meeting details
Notion Service Storing structured meeting notes and action items
Slack Service Sending notifications with summaries

The agent brief

Everything your agent needs, including the gotchas. Copy it and go.
agent-brief.md
You are helping me build the following AI agent workflow.

## Goal
Meeting Notes From YouTube To Notion: Monitors a YouTube channel for new uploads, transcribes the audio with deAPI, extracts key details via an AI agent.

## Specification
- What it does: You automatically capture new YouTube videos, transcribe them instantly, and extract titles, summaries, action items, decisions, and key topics into a structured Notion page while posting updates to Slack. This entire process runs without you needing to download files or manually review transcripts.
- Trigger: Triggered by an event (Event · on new video upload via RSS)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration and trigger monitoring
  - deAPI: Video transcription from YouTube URL
  - Anthropic Chat Model: AI analysis and extraction of meeting details
  - Notion: Storing structured meeting notes and action items
  - Slack: Sending notifications with summaries

## Known pitfalls, handle each one explicitly in your implementation
1. Transcription services may fail on long videos, so add error handling to retry or skip problematic entries.
2. Notion API limits can block bulk operations, so implement small delays between creating multiple pages if needed.
3. RSS feeds often delay updates by several minutes, so adjust the trigger interval to balance freshness and load.
4. JSON parsing errors will break the workflow, so wrap the LLM output in a try-catch block with fallback logic.

## Reference implementation
https://n8n.io/workflows/13919 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/automate-meeting-notes-from-youtube-to-notion/ via usecasesforagents.com

Frequently asked questions

Can I use a different Automation Platform than n8n?

Yes. n8n is only the example automation platform in this recipe. The same flow works with Home Assistant. Swap the automation platform connection and keep the rest of the setup as written.

Want this running in your business?

This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Get in touch →

Who it's for

Built for founders and execs who need personal productivity handled without hiring for it.

Ops-IT teams triaging their own internal requests get the same pattern, different queue.

Seen in the wild

← Back to directory