See llms.txt for all machine-readable content.

Back to Templates

Send a daily AI news digest from RSS with Google Gemini and Vivere alerts

Quick Overview

This workflow runs every morning to read multiple RSS feeds, summarise the last 24 hours of headlines with Google Gemini, email you an HTML digest, and report success or failure (including empty results) to a Vivere heartbeat monitor.

How it works

  1. Runs every day at 07:00 and sends a start ping to a Vivere heartbeat monitor.
  2. Splits your configured RSS feed list into individual URLs and fetches each feed while continuing even if some feeds error or return no items.
  3. Filters feed items to the last configured time window, deduplicates and caps the list of headlines, then routes the run based on whether there are headlines, no new headlines, or all feeds failed.
  4. If headlines exist, calls the Google Gemini (Generative Language API) to generate an HTML briefing based only on the provided headlines.
  5. Builds the email content and calculates estimated token usage and cost from Gemini’s usage metadata and your configured pricing.
  6. Sends the digest via SMTP email and posts a success ping to Vivere with item count, model, token counts, cost, and a run log line.
  7. If there are no headlines or any step errors (feed failures, Gemini errors, or email failures), sends a failure ping to Vivere with the reason and marks the execution as failed.

Setup

  1. Create a Vivere Heartbeat monitor and paste its ping URL into the workflow configuration (the pingUrl value).
  2. Add Google Gemini(PaLM) API credentials (Google AI Studio key) for the Gemini HTTP request and set the desired model name in the workflow configuration.
  3. Add an SMTP credential for sending email and set the recipient and sender addresses in the workflow configuration (emailTo and emailFrom).
  4. Replace the RSS feed URLs, topic, time window (hoursBack), and headline cap (maxHeadlines) in the workflow configuration to match your needs.
  5. (Optional) Align the Vivere monitor period/grace and any cost threshold with the workflow schedule and configured token pricing values.