Meeting Notes Summaries with Gemini AI
Daily digest of meeting summaries and action items fetched via MeetGeek and generated by Gemini AI, sent directly to your Slack channel.
founders and execsops and IT teams
What it does
Get daily meeting summaries and action items delivered straight to your Slack channel so you stay aligned without manual follow-up. This process automatically fetches notes via MeetGeek, generates concise insights with Google Gemini AI, and formats them for easy reading in Slack.
Step by step
- Configure the MeetGeek API trigger to poll for new meeting records at a fixed interval.
- Pass the raw transcript text from MeetGeek into the Google Gemini Chat Model with a structured prompt template.
- Parse the JSON response from Gemini and map fields like 'action_items' to Slack Block Kit arrays.
- Use the Slack API endpoint to post the formatted blocks to the target channel ID.
Where the LLM does the work
- Craft the system prompt for Gemini to ensure it extracts only relevant action items without hallucinating tasks.
- Refine the summary tone to match professional team communication standards during iterative testing.
- Adjust the prompt constraints if the meeting transcripts contain excessive noise or irrelevant chatter.
Watch out for
Slack Block Kit has a strict payload size limit, so truncate long summaries before formatting them for posting.
Gemini responses can vary in structure, parse the output with robust fallback logic to prevent workflow crashes.
Tools that fit
Google Gemini Chat Model LLM Generating concise summaries and action points
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Meeting Notes Summaries with Gemini AI: Daily digest of meeting summaries and action items fetched via MeetGeek and generated by Gemini AI, sent directly to your Slack channel. ## Specification - What it does: Get daily meeting summaries and action items delivered straight to your Slack channel so you stay aligned without manual follow-up. This process automatically fetches notes via MeetGeek, generates concise insights with Google Gemini AI, and formats them for easy reading in Slack. - Trigger: On a schedule (Scheduled · daily) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - MeetGeek API: Retrieving meeting summaries and action items - Google Gemini Chat Model: Generating concise summaries and action points - Slack: Sending daily notifications with summaries ## Known pitfalls, handle each one explicitly in your implementation 1. Slack Block Kit has a strict payload size limit, so truncate long summaries before formatting them for posting. 2. Gemini responses can vary in structure, parse the output with robust fallback logic to prevent workflow crashes. ## Reference implementation https://n8n.io/workflows/8116 (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-summaries-with-gemini-ai/ via usecasesforagents.com
Frequently asked questions
Can I use a different Transcription than MeetGeek API?
Yes. MeetGeek API is only the example transcription in this recipe. The same flow works with AssemblyAI, Fireflies.ai, Google Text-to-Speech API and OCR.space. Swap the transcription 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.
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.