Generate personalised sales drafts from HubSpot contacts with Gemini

Find Your AI Training Job
Chat with DigiNo Toucan and get matched to remote roles in one minute.

Sales teams spend hours researching contacts and writing cold emails that still sound generic. This AI automation reads real conversation history to build a contact persona, then writes a tailored pitch draft automatically.

What This Automation Does

Pulls a filtered list of HubSpot contacts, such as decision-makers, and processes each one individually to avoid API overload
Fetches up to 20 recent Gmail threads per contact to surface their communication style, priorities, and pain points
Uses Gemini to extract a lightweight persona covering tone, goals, buying behaviour, and decision-making style from those threads
Generates a personalised subject line and HTML email body mirrored to each contact's tone, then saves it as a reviewable Gmail draft

Tools Used

HubSpot
Gmail
Google Gemini
n8n

Work faster

Stop Typing and Start Speaking With Typeless

Typeless turns what you say into clean, formatted text in any app on Mac, Windows, Linux, iOS and Android, which it rates at 4x faster than typing. It strips filler words, keeps only your final phrasing when you change your mind mid-sentence, and works in 100+ languages. Emails, AI prompts, client messages and docs, done by voice.

Try Typeless →

Where to Get Hired for This Skill

On Contra, top freelancers across this stack have earned 113 combined verified reviews from real client projects.

Source: Contra freelancer search · refreshed 30 May 2026

Start Earning as a Freelancer on Contra

Contra is a commission-free professional network for independents. Browse live AI automation work and keep what you earn.

Join Contra Free →

How To Build It

Filter HubSpot contacts by role

Connect HubSpot so the workflow queries only a targeted segment, such as contacts flagged as decision-makers, keeping the output list tight and the run predictable for your client's use case.

Fetch recent Gmail threads per contact

For each contact in the list, retrieve up to 20 of their most recent Gmail conversations so the AI has real signal about how they write, what they care about, and how they respond.

Extract a persona from conversation history

Feed the Gmail threads into Gemini via an information extraction step that outputs structured persona fields: communication preferences, decision style, pain points, motivations, and market awareness.

Set the offer and contact variables

Define the core pitch details once, including the contact's first name, last name, email address, and the specific offer being promoted, so every generated email references accurate, client-supplied context.

Generate and save the Gmail draft

Pass the persona and offer into Gemini to produce a subject line and HTML email body that mirrors the contact's tone, then save the output as a Gmail draft so the sales rep can review and send without rewriting from scratch.

Pitfalls

Gmail OAuth tokens expire silently: if a client's token lapses mid-run, drafts stop being created with no visible error, so build in a connection health check and alert before each campaign batch runs.
Persona quality degrades when a contact has fewer than three or four Gmail threads to analyse: coach your client to use this on warm or re-engagement lists, not cold contacts who have never exchanged email with them.
Gemini can mirror a contact's casual or blunt tone too literally and produce a draft that feels off-brand: set clear tone guardrails in the prompt and always frame the draft as a starting point requiring human review, not a send-ready output.

FAQ

Can I build this without coding?

Yes. The entire workflow is configured through visual forms and prompt fields rather than written code. You need to understand how to connect OAuth apps and structure an AI prompt, but no programming language is required.

How long does it take to build and deliver?

A clean build typically takes four to six hours including connecting the client's HubSpot and Gmail accounts, writing the persona extraction prompt, and testing on a small contact batch. Allow extra time if the client needs custom offer variables or brand tone guidelines baked in.

What can I charge for this service?

Pricing is your decision based on your market and positioning. A useful framing is to anchor the value on time saved per campaign rather than on the tool itself, since sales teams can immediately see how many hours of manual research this replaces per rep.

Which tools are required versus optional?

HubSpot and Gmail are both required because the workflow reads contact data from one and both reads threads from and writes drafts to the other. Gemini is the default AI layer, but a freelancer comfortable with prompt engineering could swap it for a different model if the client already has a preferred provider.

This is original DigiNo analysis. The underlying automation pattern is a community workflow template – view the original on n8n.