Stock News Alerts
Polls stock news every 15 minutes, summarizes articles via LLM, and sends real-time alerts to Telegram while logging them in Google Sheets.
What it does
Get instant stock news updates delivered directly to your Telegram chat every 15 minutes with concise summaries that highlight only the latest changes. This workflow automatically logs each alert in Google Sheets so you can track market movements without missing a beat.
Step by step
- Configure the n8n Cron node to trigger every 15 minutes for polling.
- Set up the HTTP Request node to fetch data from the Google Alerts RSS feed URL.
- Define the Jina AI API endpoint and headers for extracting text from article URLs.
Where the LLM does the work
- Prompt the OpenRouter model with specific instructions to generate concise stock-relevant summaries.
- Instruct the LLM to output structured data that can be easily parsed by subsequent nodes.
Watch out for
Jina AI requests can fail on paywalled content so add error handling to skip inaccessible URLs gracefully.
Telegram message length limits exist so truncate or summarize long outputs to avoid API rejection errors.
Tools that fit
OpenRouter Chat Model LLM Summarizing article content via LLM
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 Stock News Alerts: Polls stock news every 15 minutes, summarizes articles via LLM, and sends real-time alerts to Telegram while logging them in Google Sheets. ## Specification - What it does: Get instant stock news updates delivered directly to your Telegram chat every 15 minutes with concise summaries that highlight only the latest changes. This workflow automatically logs each alert in Google Sheets so you can track market movements without missing a beat. - Trigger: On a schedule (Scheduled · every 15 minutes) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - n8n: Workflow orchestration platform - Google Sheets: Storing alerts and filtering duplicates - Jina AI: Extracting main body text from URLs - OpenRouter Chat Model: Summarizing article content via LLM - Telegram: Sending real-time notifications ## Known pitfalls, handle each one explicitly in your implementation 1. Jina AI requests can fail on paywalled content so add error handling to skip inaccessible URLs gracefully. 2. Telegram message length limits exist so truncate or summarize long outputs to avoid API rejection errors. ## Reference implementation https://n8n.io/workflows/5712 (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/automated-stock-news-alerts/ 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.
Who it's for
Built for founders and execs who need data & analytics handled without hiring for it.
Works just as well for personal use, no business context needed.