Cold Calling Pipeline with Apify and WhatsApp
Automates cold outreach by scraping prospects with Apify, researching them via OpenAI RAG, and sending personalized WhatsApp messages.
What it does
You automatically find high-quality prospects using Apify, research them with OpenAI to create personalized messages, and send them via WhatsApp without manual effort. The workflow handles initial responses and schedules follow-ups while tracking performance so you can optimize your outreach continuously.
Step by step
- Configure Apify actors to extract structured lead data from target websites and export it to a CSV or JSON format.
- Set up a Google Sheet as the central database to store lead details, interaction status, and campaign metrics.
- Implement webhooks in the WhatsApp Business API to capture incoming messages and update the Google Sheet with response timestamps.
Where the LLM does the work
- Generate personalized cold call scripts by combining scraped company data with real-time news using a RAG pipeline.
- Classify inbound WhatsApp replies into intent categories such as interested, not now, or spam to trigger appropriate follow-ups.
- Draft concise and engaging text messages that adapt tone based on the prospect's industry and previous interaction history.
Watch out for
WhatsApp has strict anti-spam policies so you must include opt-out mechanisms and avoid sending identical bulk messages to prevent number bans.
Apify scraping can fail if target websites change their structure, add a monitoring script that alerts you when extraction rates drop unexpectedly.
Tools that fit
OpenAI Chat Model LLM RAG content generation and personalization
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 Cold Calling Pipeline with Apify and WhatsApp: Automates cold outreach by scraping prospects with Apify, researching them via OpenAI RAG, and sending personalized WhatsApp messages. ## Specification - What it does: You automatically find high-quality prospects using Apify, research them with OpenAI to create personalized messages, and send them via WhatsApp without manual effort. The workflow handles initial responses and schedules follow-ups while tracking performance so you can optimize your outreach continuously. - Trigger: On a schedule (Scheduled · daily) - Autonomy: Fully hands-off - Expected setup effort: a few focused days - Tools/services involved: - Apify: Prospect scraping and data collection - OpenAI Chat Model: RAG content generation and personalization - WhatsApp: Automated message delivery to prospects - Google Sheets: Prospect storage and campaign tracking ## Known pitfalls, handle each one explicitly in your implementation 1. WhatsApp has strict anti-spam policies so you must include opt-out mechanisms and avoid sending identical bulk messages to prevent number bans. 2. Apify scraping can fail if target websites change their structure, add a monitoring script that alerts you when extraction rates drop unexpectedly. ## Reference implementation https://n8n.io/workflows/5449 (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-cold-calling-pipeline-with-apify-and-whatsapp/ via usecasesforagents.com
Frequently asked questions
Can I use a different Web Scraping than Apify?
Yes. Apify is only the example web scraping in this recipe. The same flow works with Airtop, Bright Data, Decodo and Firecrawl. Swap the web scraping 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 sales teams who want the prep work done before they pick up the phone.
Founders and execs get the same output without having to ask someone else to run it.