Weekly Business Metrics Report Generator
Every Monday at 08:00, it aggregates Stripe revenue, Notion pipeline.
What it does
Every Monday at 08:00, you receive an emailed HTML report with executive analysis of your Stripe revenue and Notion pipeline metrics. The agent automatically aggregates data from Stripe, Notion, and Google Sheets, normalizes the figures for clarity, posts a summary to Slack, and delivers everything via SendGrid.
Step by step
- Configure a cron trigger to execute the workflow every Monday at 09:00 UTC.
- Use API clients for Stripe, Notion, and Google Sheets to fetch raw transaction and page data.
- Write Python code to normalize timestamps and currency values into a unified JSON structure.
- Send the aggregated JSON payload to the Anthropic API with a fixed system prompt template.
Where the LLM does the work
- Prompt the LLM to interpret the normalized metrics and identify key trends or anomalies in business performance.
- Instruct the model to generate a concise executive summary that highlights wins, risks, and actionable next steps.
- Ask the LLM to suggest specific narrative phrasing for the HTML report based on the tone of the data.
Watch out for
Notion database schemas change frequently so add validation checks to ensure required properties exist before processing.
LLM output length may exceed email body constraints so truncate or summarize long responses before HTML generation.
Tools that fit
Anthropic Chat Model LLM Generate executive narrative from aggregated data
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 Weekly Business Metrics Report Generator: Every Monday at 08:00, it aggregates Stripe revenue, Notion pipeline. ## Specification - What it does: Every Monday at 08:00, you receive an emailed HTML report with executive analysis of your Stripe revenue and Notion pipeline metrics. The agent automatically aggregates data from Stripe, Notion, and Google Sheets, normalizes the figures for clarity, posts a summary to Slack, and delivers everything via SendGrid. - Trigger: On a schedule (Scheduled · weekly Monday 08:00) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - Stripe: Fetch revenue and transaction data - Notion: Retrieve pipeline and deal data - Google Sheets: Read operational metrics like NPS and uptime - Anthropic Chat Model: Generate executive narrative from aggregated data - SendGrid: Deliver styled HTML report via email ## Known pitfalls, handle each one explicitly in your implementation 1. Notion database schemas change frequently so add validation checks to ensure required properties exist before processing. 2. LLM output length may exceed email body constraints so truncate or summarize long responses before HTML generation. ## Reference implementation https://n8n.io/workflows/15791 (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/weekly-business-metrics-report-generator/ via usecasesforagents.com
Frequently asked questions
Can I use a different Payments than Stripe?
Yes. Stripe is only the example payments in this recipe. The same flow works with PayPal and Razorpay API. Swap the payments 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.
Finance teams can run the same extraction-and-file pattern on their own paperwork.
Sales teams can plug this into their own CRM and call cadence just as easily.