Research prospects and draft personalized cold emails automatically

The system researches each prospect's website for a real business problem, then writes a personalized cold email pitch.

How the work actually flows

It branches. Exactly one path is taken; runs once per each lead in the list.

Pattern: Exclusive Choice (4) · Multiple Instances with a priori Design-Time Knowledge (13)

flowchart TD trig(("user starts campaign run")):::human s0[["filter leads missing info"]]:::mi s1["scrape prospect website"]:::svc s2["find operational problem"]:::svc s3["draft personalized email"]:::svc s4[("save draft for review")]:::store trig --> s0 s1 --> s2 s2 --> s3 s3 --> s4 gx{"× lead has valid email and site"}:::gate s0 --> gx p00["skip lead"]:::task gx -->|"invalid lead"| p00 p10["continue research"]:::task gx -->|"valid lead"| p10 p00 --> s1 p10 --> s1 out[/"personalized cold email draft ready"/]:::out pay{{"outreach that sounds researched not generic"}}:::pay s4 --> out out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
An outside serviceRuns once per itemA personA record or sheetOne path onlyResultPayoff
Build size
Advanced

A larger build with multiple systems, AI reasoning, and custom rules.

Business functions
Email AutomationSpreadsheet & Database OpsWeb Scraping & Data CollectionScheduling & Calendar
Connects
Google SheetsOpenAIAnthropicGmail

The problem it solves

Generic cold emails that just compliment someone's website rarely get a reply. Actually researching each prospect to find a real reason to reach out takes hours you don't have, especially when you're sending to a whole list.

Who it fits

Sales teams and agencies doing outbound outreach who want emails that sound researched, not templated.

How it works

  1. Starting from a list of leads in Google Sheets, the system filters out any without a working email or website
  2. It scrapes each prospect's website for text and links
  3. AI analyzes the site to find a specific operational problem worth mentioning
  4. A second AI writes a natural, personalized email based on that insight
  5. The finished email and lead data are saved to Google Sheets, and a draft is sent to you by Gmail for review
What you get

Personalized draft emails ready for your review

You get personalized cold email drafts researched from each prospect's website, ready for you to review and send.

What you get

A personalized cold email draft for each qualified lead, logged in Google Sheets for your outreach campaign.

What you need

A Google Sheets account, an OpenAI API key, an Anthropic API key, and a Gmail account.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Back to the AI Playbook