← Back to directory
Personal Productivity Medium to set up AI workflow Extract to Structured

Meeting Notes To Action Items

Source reviewed Updated 2026-07-07

Receives meeting notes via webhook, uses Gemini to extract action items and decisions, then creates tasks in Google Tasks.

What it does

Stop manually transcribing meeting notes; this workflow instantly converts your raw webhooks into actionable tasks in Google Tasks using Gemini to extract key decisions and summaries. You get a generated summary document in Google Docs and follow-up emails via Gmail sent automatically so nothing slips through the cracks.

Step by step

  1. Configure the webhook node to accept POST requests with a JSON payload containing the raw meeting notes.
  2. Set up service account credentials for Gmail, Google Tasks, and Google Docs within n8n to enable API access.
  3. Define the structured output schema in the Gemini node to enforce a consistent JSON structure for action items.

Where the LLM does the work

  • Prompt the Gemini model with specific instructions to distinguish between definitive decisions and tentative discussion points.
  • Instruct the LLM to infer missing context for action items, such as assigning implicit owners based on meeting roles if not explicitly stated.
  • Ask the model to generate a concise executive summary that captures the tone and key outcomes without listing every detail.

Watch out for

Service account permissions might fail if the Google Workspace domain settings restrict API access, so verify the OAuth scopes include full drive and gmail access.
Large meeting transcripts can exceed token limits, so implement a chunking strategy or summary-first approach before sending data to the LLM.
Emails sent via automation may land in spam folders if they lack proper authentication headers, so ensure SPF and DKIM records are correctly configured for your domain.

Tools that fit

n8n Service Workflow orchestration and trigger handling
Google Gemini Chat Model LLM Analyzing notes to extract action items and summaries
Gmail Service Sending personalized follow-up emails
Google Tasks Service Creating structured tasks from action items
Google Docs Service Generating meeting summary documents

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 To Action Items: Receives meeting notes via webhook, uses Gemini to extract action items and decisions, then creates tasks in Google Tasks.

## Specification
- What it does: Stop manually transcribing meeting notes; this workflow instantly converts your raw webhooks into actionable tasks in Google Tasks using Gemini to extract key decisions and summaries. You get a generated summary document in Google Docs and follow-up emails via Gmail sent automatically so nothing slips through the cracks.
- Trigger: Triggered by an event (Event · on webhook receipt of meeting notes)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration and trigger handling
  - Google Gemini Chat Model: Analyzing notes to extract action items and summaries
  - Gmail: Sending personalized follow-up emails
  - Google Tasks: Creating structured tasks from action items
  - Google Docs: Generating meeting summary documents

## Known pitfalls, handle each one explicitly in your implementation
1. Service account permissions might fail if the Google Workspace domain settings restrict API access, so verify the OAuth scopes include full drive and gmail access.
2. Large meeting transcripts can exceed token limits, so implement a chunking strategy or summary-first approach before sending data to the LLM.
3. Emails sent via automation may land in spam folders if they lack proper authentication headers, so ensure SPF and DKIM records are correctly configured for your domain.

## Reference implementation
https://n8n.io/workflows/5904 (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/meeting-notes-to-action-items/ 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.

Sales teams can plug this into their own CRM and call cadence just as easily.

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

Seen in the wild

← Back to directory