Build a five-email onboarding sequence with stop rules and a dry-run cron job, using a copy-paste prompt for your AI coding tool
A beginner guide for first-time SaaS builders: pick one first-win action, log signups and sends, map five plain emails over 14 days with stop rules, send them from a scheduled job after a dry run, and measure activation instead of opens.
Evidence: The source shows its work: steps, screenshots, code or data you can inspect.
The business problem
New sign-ups to a small SaaS often never come back after day one, and founders who build with AI coding tools rarely set up a lifecycle email system that stops when the user has already succeeded.
What was tried
1. Choose one first-win action that shows the product's value. 2. Store signup time, activation time and email opt-outs, plus an email log so no message is sent twice. 3. Map a short sequence (five emails over 14 days) and write stop rules, for example stop once the user activates or unsubscribes. 4. Write short plain-text templates. 5. Send from a scheduled job (the guide uses Vercel Cron or Supabase Cron, with Resend as the sender in its example), and run it in dry-run mode first. 6. Add unsubscribe links and a postal address to meet commercial email rules (CAN-SPAM, Gmail sender guidelines; the guide says this is not legal advice). 7. Review activation rate, time to first win and replies each week rather than open rates. The guide includes SQL snippets, a send example and a copy-paste prompt to have Cursor, Claude Code, Lovable, Bolt, Replit or v0 implement the system.
What was reported (not reported)
Not reported. This is a how-to guide with no metrics, case study or before-and-after data.
Limitations
A generic beginner guide from a new author account (joined October 2026) with several similar guides; no results from any real product. AI is only used to implement the system through the supplied prompt, and the post does not say whether AI wrote the guide. Code generated from the prompt still needs checking, especially the stop rules and duplicate-send guard. Legal points are general and not legal advice.
What you need
A SaaS with a database you control, an email sending service, a scheduler (cron), and an AI coding tool if you use the supplied prompt.
Run the job in dry-run mode and inspect the email log before turning on real sends.
Sources
- DEV Community (Vishal Chauhan, siteory) ↗ Tutorial, published October 21, 2026
Source published: October 21, 2026. Last reviewed here: October 24, 2026. Spot a mistake? Tell us.
Tools in this workflow
- Vercel: Cron optionTry Vercel
- Cursor: One of the AI coding tools the prompt is written forTry Cursor
- Claude Code: One of the AI coding tools the prompt is written forTry Claude Code
- Supabase: Database and cron optionTry Supabase
- Resend: Email sending in the exampleTry Resend
Get new workflows like this by email
A short selection of the most useful new workflows, including the ones that did not work. Free, and you can unsubscribe at any time.
Related workflows
Build an n8n node with Cursor in an hour, then cold-email the people selling AI posting templates
The founder of Postiz, an open-source social scheduler, noticed n8n template sellers teaching AI social posting, had Cursor turn his public API into an n8n node, and cold-emailed those creators with an offer. He reports monthly revenue roughly doubling.
Put an AI agent on your highest-intent page to qualify and book buyers, plus a personalised self-serve page a person approves
SaaStr's account of a year of inbound AI: an agent on the sponsor page qualifies visitors and books meetings, and a second path sends a company-specific page, watches the visit, and drafts a pitch that a person approves and sends.
Cut LLM costs in a small SaaS with flex-tier fallback, cache-friendly prompt order, side-by-side model migrations and backend circuit breakers
A bootstrapped founder's four habits for the AI calls inside his product: try the cheaper flex tier first and fall back on rate limits, order prompts so the long repeated part is cached, run old and new models side by side before switching, and cap spend in the backend.
Test a Claude-written sales page headline against your own (copywriter reports a win, and a loss on subject lines)
A freelance-copywriting newsletter author gave Claude Opus 4.6 basic context about his offer, put its headline up against his own on his sales page, and reports about 50% more conversions. He says AI lost to him on email subject lines.