Transform NASA DONKI Space Alerts to Japanese with GPT-4 for Slack and Sheets

Who’s it for

Teams that care about space-weather impact—SRE/infra, satellite ops, aviation, power utilities, researchers—or anyone who wants timely, readable alerts when NASA publishes significant solar events.

How it works / What it does

Every 30 minutes a Cron trigger runs, the NASA DONKI node fetches the past 24 hours of space-weather notifications, and a code step de-duplicates, labels event types, and assigns a severity (CRITICAL / HIGH / OTHER). A Switch routes items:

• CRITICAL/HIGH → an LLM (“AI Agent”) produces a concise Japanese alert → Slack posts with local time and source link.
• OTHER → an LLM creates a short summary for record-keeping → a small merge step prepares fields → Google Sheets appends a new row.
  Sticky notes in the canvas explain the schedule, data source, and overall flow.

How to set up

1. Add credentials for Slack, Google Sheets, and OpenAI (or compatible LLM).
2. Open the Slack nodes and select your workspace + target channel.
3. Select your Google Sheet and worksheet for logging.
4. (Optional) Adjust the Cron interval and the NASA lookback window.
5. Test with a manual execution, then activate.

Requirements

• Slack Bot with permission to post to the chosen channel
• Google account with access to the target Sheet
• OpenAI (or API-compatible) credentials for the LLM nodes
• Internet access to NASA DONKI (no API key required)

How to customize the workflow

• Tweak severity rules inside the Analyze & Prioritize code node.
• Edit prompt tone/length in each AI Agent node.
• Change Slack formatting or mention style (@channel vs none).
• Add filters (e.g., alert only on CME/FLR) or extend logging fields in the merge step.