Review drafts before reaching out
I built this workflow to prepare Gmail drafts from a researched lead list. It removes duplicate email addresses within a run, checks suppression and recent draft history, and caps the batch before the model runs. You review the wording and choose whether to send.
Buy the download · $19 The n8n download, $19 USD
The question
this build answers
How do I draft personalised cold emails from a lead list without re-contacting someone who opted out or was drafted to recently?
From the first trigger
to the finished job.
The working version, step by step.
Trigger it by hand or on a schedule
I wire two triggers, one you run by hand and one that fires weekly. Nothing drafts until one of them goes. I put your name, your one-line pitch, your value proposition, how many drafts per run, and how many days before a contact can be redrafted in one settings node.
Check the suppression list first, no exceptions
Before anything else runs, every lead is checked against a suppression list matched on email. Anyone on it is dropped here. There is no override, and there is no path in this workflow that skips this check.
Filter by cooldown in code, not a model
The workflow removes duplicate normalised email addresses within the current run, then checks recent records in SentLog against your cooldown setting. A contact can be drafted again after that window. Keep the history complete and avoid overlapping runs.
Cap the run before a token is spent
I trim the surviving list to your maximum drafts per run before the AI is ever called, so a big list can never spend a big AI bill in one run. Suppression, cooldown and the cap all run upstream of the model, in that order.
Draft one email, one call to action
The prompt asks OpenAI for a short subject and body using the supplied research note. That instruction cannot guarantee factual accuracy, so check every draft for invented claims, prices or promises. The output stays in Gmail drafts; the workflow has no send path.
Log the draft, then remember it
I append the drafted lead, subject, timestamp and Gmail draft ID to a Draft Log tab, so you have a visible record without opening Gmail. I write the email and the current timestamp back into the Sent Log, which is what makes the cooldown check mean something on the next run.
The n8n download, $19 USD
Draft cold emails from Google Sheets with AI, suppression checks and a cooldown
Fifteen working nodes make up this one, with the setup written on the canvas and a guide I wrote for every node. It checks your suppression table before it ever asks the model for a word. This purchase covers the files; connect your own accounts, or arrange hands-on installation as a separate service with its own scope and price.
Buy the download · $19Need more workflows? $99 USD
Everything Pack
I include seventeen products and twenty-five workflow files for bookings, finance, leads and admin. Choose the parts your business needs and configure each workflow separately with its own guide.
Buy the Everything Pack · $99What the manual version costs
I'm not going to give you a minutes-per-email figure, because I haven't measured one on my own outreach and I'd only be borrowing somebody else's number. What I can tell you is the shape of the cost: without a suppression list and a cooldown, a lead list gets redrafted every time you rerun it, and the version that actually costs you is the one where the same prospect gets pitched twice in the same week.
The other cost is the one that never shows up in a report until somebody complains: drafting to a contact who already asked to be left alone. I'd rather check the suppression list before the model is ever called than have the conversation that follows if it isn't.
The parts that break
Within one run, duplicate normalised email addresses are removed before drafting. Separate runs can still overlap before their history is written, so keep one run active at a time and maintain the SentLog records used by the cooldown check.
The suppression check matches on the exact email address in the row. A prospect who opts out from a personal address and gets re-added later under a work address slips past it, so I'd keep the suppression list as the place you add every address you have for someone, not just the one that opted out.
A thin research note gives the model little to work with. I ask it to keep the message brief and use the supplied facts, but every draft needs a human check before sending.
What it costs to run
The workflow uses your n8n, Google and OpenAI accounts. The cap limits how many leads reach the model in a run; provider charges remain separate from the download.
Maintain your lead research, suppression list and recent-contact records. I include sample CSVs and setup instructions, while the accuracy of those records remains part of your outreach process.
Before you connect a prospect list
I would start with your own addresses and read the resulting drafts before connecting a prospect list.
Before you spend anything
The fit matters.
Who should not buy this
If you send fewer than a handful of first-touch emails a month, this buys you machinery to maintain for a problem you don't have yet, and a list that short is faster to draft by hand than to configure.
If you don't already have a lead list with a real fact gathered per lead, this expects that input to exist rather than sourcing it for you. Pair it with a prospecting workflow, or start there first.
If what you actually want is automatic sending, this isn't that, on purpose. It drafts, it never sends, and turning a draft into a send stays a decision you make yourself, message by message.
Yours to keep
What lands
on your desk.
- An importable n8n workflow, setup guide and start-here instructions
- Sample lead and suppression CSV files
- Duplicate, suppression and cooldown checks before the model call
- Gmail draft creation with draft and recent-contact logs
See the work
Open the proof.
Published case studies of running systems. Each links to the thing itself.
A few useful
answers.
Does it ever send the email automatically?
It never sends. It only ever creates a Gmail draft, and there is no send path in this workflow, not even behind a setting, so turning a draft into a send is a decision you make yourself.
What stops it drafting to someone who opted out?
A suppression list is checked first, matched on email, before anything else runs, and anyone on it is dropped right there with no override.
Can a contact be drafted more than once?
The workflow removes duplicate normalised email addresses within one run and checks recent draft history against your cooldown. Later redrafts are allowed after that window. Keep the history intact and avoid concurrent runs.
Can the model invent facts?
The model can still invent facts. The prompt asks for the research you supplied, but it cannot guarantee the result. Review every Gmail draft for unsupported claims before sending.
What comes with the download?
The workflow, setup and start-here guides, sample lead and suppression files are included. You connect your own n8n, Google and OpenAI accounts.
Licence and support
Personal and commercial use on your own instances and for your own clients. Do not resell or redistribute the files themselves.
Email support@fractionalhq.uk and include your order email.
Ways to get this
Download it, have me install it,
or have me build it to fit.
Download it
$19 USD
The workflow files and the setup guide, to import into your own n8n.
Buy the download · $19Have me install it
$15 USD
I can install it on your own n8n and accounts for $15. You sign in and paste your keys into n8n by your own hand while I do the rest. After a test run with you, I fix anything in my install that breaks in the first 14 days.
Book the install · $15Have me build it to fit
Quoted to your job
Tell me what your version needs to do. One line is enough to start.
Start a brief


