Skip to content
Web&Leads

Our product

An AI outbound engine that finds, analyzes and emails prospects on autopilot

We built a fully automated outbound pipeline for Listrino. It discovers hosts city by city, analyzes their listings with AI, scores each lead, publishes a personal audit, sends a two-step email sequence and stops follow-ups the moment someone replies.

Client
Listrino
Industry
Short-term rentals, SaaS
Services
AI automationAI software developmentSEO and AI search (GEO)
Year
2026

Results

  • 1person runs the full pipeline from the command line
  • < $15monthly LLM cost target at 100 leads per day
  • 2step sequence, auto-cancelled on reply
An AI outbound engine that finds, analyzes and emails prospects on autopilot

The challenge

A new SaaS has no audience. Listrino needed a way to reach hosts who would benefit from a listing audit, without hiring a sales team and without sending generic spam.

The idea: show value first. Analyze a host's listing for free, publish a personal report, and send it with a short, relevant email. Doing that by hand for hundreds of hosts was impossible.

Our approach

We built the growth engine as a set of small, testable steps behind one command:

  1. Discover. An Apify actor finds professional hosts in the four largest cities of a country. We keep hosts rated between 4.2 and 4.8 with at least 20 reviews: good enough to care, with room to improve. Anyone emailed in the last three months is skipped.
  2. Analyze in batches. Listings are scraped in batches of 25 per actor run and analyzed with the same grounded AI pipeline as the product, with the expensive photo audit switched off to keep costs low.
  3. Score. Each lead gets an explainable HOT, WARM or LOW score with the factors behind it.
  4. Publish. Each host gets a personal public audit page on listrino.com.
  5. Email. An AI writes a short day-0 email from a version-controlled prompt file, wrapped in a branded template. Day-7 is scheduled in advance through Resend.
  6. Handle replies. A signed inbound webhook detects replies, cancels the scheduled follow-up and forwards a notification. Replies are answered from a dashboard so threads stay intact. One-click unsubscribe is built in.
  7. Turn data into content. Market-level findings are exported as data files for blog posts, social posts and newsletters.

Everything runs in an isolated database, with a separate scraping token and sending subdomain, so outbound can never affect the product or its email reputation.

The results

  • One person runs a full outbound operation that would normally need a small team.
  • LLM costs are designed to stay under $15 per month at 100 leads per day.
  • Every email carries real value, a personal report, instead of a sales pitch.

What clients can take from this

Most companies have a version of this problem: leads to research, qualify and follow up, with too little time. We build the same kind of system for clients with AI automation, using n8n, Make or custom code depending on volume and control.

Stack

  • TypeScript CLI
  • Apify
  • OpenAI
  • Resend
  • Svix webhooks
  • Neon Postgres
  • Drizzle ORM
  • Next.js

Have a project or an AI idea?

Tell us what you want to fix or build. We reply within one business day with honest next steps.