Cold Email Research Agent
Researches each prospect and writes a grounded first line and 3-step sequence: email 1 as a Gmail draft, follow-ups in your sheet. Role: Prospect researcher.
Trial opens soon
We're connecting secure checkout for the 7-day free trial. Leave your email and we'll write once, on the day it opens.
Batch of 10 leads startedFrom your Leads sheet, status = new
LoggedResearched lumen-analytics.exampleRecent product launch and 2 open sales roles
Draft readyFirst line + 3 emails for Sara Kim, Head of GrowthFit 9/10 · Gmail draft of email 1 created
Draft readyNo email address for “Oakfield Bakery”Row marked missing_email
Needs youBatch finished7 drafted, 2 low fit, 1 missing email
Logged
Implementation in your business
Between your lead list and Gmail: it reads new rows in a Google Sheet, researches each company's website and leaves Gmail drafts for good fits.
Where it plugs in
The prospecting core of the AI SDR on its own: Google Sheet of leads → website research → first line, 3 emails, fit score → email 1 as a Gmail draft, emails 2-3 in the sheet.
What it needs
- n8n (Cloud or self-hosted)
- Google account: Sheets + Gmail
- OpenAI API key (Tavily optional, for news)
- Your offer, ICP and signature (Config)
What it outputs
- Gmail draft of email 1 (with the first line); emails 2-3 in your sheet
- Fit score and reason per lead
- Status per row: drafted, low_fit, missing_email, error
Time saved (estimate)
≈ 43 h
per month at 50 prospects a week, 15 min by hand vs 3 min review. See assumptions.
Setup: about 15 minutes on n8n Cloud
Three steps, no code. The setup guide has the full checklist.
Pick the Cold Email Research Agent
Start the trial on Starter (this employee) or Workforce (all five). The download link and guide arrive by email.
Import it
n8n Cloud or self-hosted: Workflows → Import from file. No n8n? Paste the instructions into a Custom GPT or Claude Project.
- 1 workflow file
- Sheet template (CSV)
Connect your tools
Sign in once per service, then fill in the Config node with your details.
- Google Sheets
- OpenAI
- Gmail
- Config: your details and rules
How it works
Import-tested and test-executed with stubbed services on n8n 2.44 before release.
Grounded personalisation. The model only sees the prospect's own website (and news if you enable Tavily) and is told never to invent facts.
Fit scoring. Each lead gets a 1-10 ICP score with a reason; poor fits are skipped.
Drafts only. A Gmail draft of email 1 for good fits; emails 2-3 and everything else logged back to the sheet. Nothing is sent automatically.
What you get
- cold-email-research-agent.n8n.json: Leads sheet → website (+ optional news) → AI first line, 3 emails, fit score → Gmail draft of email 1 → sheet (emails 2-3)
- No-code version: Custom GPT / Claude Project instructions
- Prompt library, sheet templates and a PDF setup guide
What it's worth to you
The value is time: the employee does the first pass and you keep the review. Two worked examples, every input an assumption:
| Assumption (estimate) | Light outbound | Active outbound |
|---|---|---|
| Prospects researched per week | 20 | 50 |
| Manual minutes per prospect | 8 | 15 |
| Review minutes (you still review) | 3 | 3 |
| Share the employee handles | 100% | 100% |
| Hourly cost of whoever does it | $25 | $40 |
| AI running cost per prospect | $0.05 | $0.05 |
| Hours taken over per week | 1.7 h | 10.0 h |
| Value of that time per month, after AI costs | ≈ $176 | ≈ $1,723 |
| After the $19 Starter plan | ≈ $157 | ≈ $1,704 |
Try your own numbers
More assumptions
Formula: hours/week = volume × share handled × (manual − review minutes) ÷ 60 · hours/month = hours/week × 52 ÷ 12 · net = hours/month × hourly cost − AI running costs − plan cost. Time saved only; no claims about revenue, replies or hiring outcomes.
Questions
What's the difference with the AI SDR?
The AI SDR includes this exact workflow plus a Reply Handler that classifies replies and drafts answers in-thread. On Starter you can pick either; Workforce includes both.
Do I need n8n?
For the automated version, yes: n8n Cloud or the free self-hosted edition. Every employee also ships a no-code version for a ChatGPT Custom GPT or a Claude Project.
Does it act on its own?
It works in drafts and logs. Anything that reaches a customer, candidate or prospect is a draft you review and send.
What does it cost?
Starter is $19/month for this employee, Workforce $49/month for all five. Both have a 7-day free trial. You also pay your own AI usage (usually cents per item) and your n8n plan if you use n8n Cloud.
Guardrails
- Cold email rules differ by country (GDPR/ePrivacy, CAN-SPAM). Contact business prospects with a legitimate interest and honour opt-outs. Not legal advice.