Skip to content

Research backed cold email team

Several small agents each take a batch of leads, research the company and its ads, and write a personal cold email. A stronger model reviews each email and a person approves before anything is sent.

SalesWorks with Claude CodeCommunity example
Build your promptSee requirements

What it does

  • Splits the day's leads into batches
  • Researches each site and its public ads
  • Writes an email tied to a real gap
  • Has a reviewer model check every draft

Your approval boundaries

Approval required

These actions always wait for your yes:

  • Sending any email
  • Adding leads to a sequence

You decide what happens next.

More about this workflow

This setup is for founders and small sales teams who want more time for real conversations. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it splits the day's leads into batches. Next, it researches each site and its public ads. Then it writes an email tied to a real gap. Finally, it has a reviewer model check every draft. It works with your CRM, web search and email, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before sending any email and adding leads to a sequence, and says plainly if a step cannot be undone.

“Opus reviews every email”
hritik @AI_Bhaiiii · Sep 21, 2026
Before you startCRM · Web search accessScoped permissionsClaude Code
Explore required tools and model recommendations

Tools and access

  • HubSpot CRM

    Handles the crm part of this job. Grant read scopes, plus notes write.

    API required: Yes. Needs a HubSpot private app or OAuth app with the CRM scopes you choose.

    Sign up: HubSpot CRM

  • Web search

    Handles the web search part of this job. Grant public search results only.

    API required: Optional. Built into most agent harnesses. A standalone search API needs its own key.

    No sign-up needed

  • Gmail

    Handles the email part of this job. Grant read-only plus compose (drafts) scopes.

    API required: Yes. Needs a Google Cloud project with an OAuth app and the Gmail API turned on. The agent signs in through OAuth with only the scopes you pick.

    Sign up: Google Workspace

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Claude Sonnet 5.5

Good balance of speed and quality for briefs and drafts.

$2 per million input tokens, $10 per million output tokens.

Anthropic docs as of October 11, 2026

Cheaper backup

GPT-6 Luna

Very low cost per token for simple research summaries.

$0.10 per million input tokens, $0.50 per million output tokens, for prompts up to 272K tokens.

OpenAI docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

what you sell

size, industry, role

CRM view or inbox label

e.g. 45 leads

2Your prompt

4 of 4 still empty
Fill these in before you run it: [YOUR BUSINESS AND OFFER: what you sell] [YOUR IDEAL CUSTOMER: size, industry, role] [WHERE NEW LEADS ARRIVE: CRM view or inbox label] [DAILY LIMIT: e.g. 45 leads] You are the Research backed cold email team agent. Several small agents each take a batch of leads, research the company and its ads, and write a personal cold email. A stronger model reviews each email and a person approves before anything is sent. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Splits the day's leads into batches - Researches each site and its public ads - Writes an email tied to a real gap - Has a reviewer model check every draft What you must never do without a yes from a person: - Sending any email - Adding leads to a sequence Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: Claude Code

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect HubSpot CRM with its own login, not yours. Grant read scopes, plus notes write.
  2. 2Set up Web search. Keep it to public search results only.
  3. 3Connect Gmail with its own login, not yours. Grant read-only plus compose (drafts) scopes.
  4. 4Paste the prompt where your harness takes instructions. See the note under the Copy button.
  5. 5Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  6. 6Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access18 / 30

Can draft things that send or spend, so it sits close to risky actions.

Human approval30 / 30

Waits for a yes on: sending any email, adding leads to a sequence.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope16 / 20

Runs on its own login across 3 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Access: Take away its ability to send, post or spend. Let it only write drafts, and have a person press send or pay from their own account +6
  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
  • Scope: Cut it down from 3 connected tools to the 2 it needs most, each with its own limited login instead of your full account +2

Do all of these to reach 89, up from 78.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Research backed cold email team](https://trustcase.dev/badge/research-backed-cold-email-team.svg)](https://trustcase.dev/use-cases/research-backed-cold-email-team)
HTML
<a href="https://trustcase.dev/use-cases/research-backed-cold-email-team"><img src="https://trustcase.dev/badge/research-backed-cold-email-team.svg" alt="Trustcase trust score for Research backed cold email team" height="20"></a>

More sales workflows

  • New subscriber pitch drafter

    Watches for new newsletter subscribers, checks if they fit your ideal customer, and drafts a personal pitch in your voice. You decide who actually gets it.

  • Listing inquiry responder

    Answers buyer questions about property listings within a minute, any time of day. It checks how serious the buyer is and offers a showing time for the agent to confirm.

  • Local B2B lead finder

    Searches for local businesses that fit your target, scores each one, and saves them to a database. Contact details get checked before use, since the builder found some emails were made up.

  • Ideal customer profile builder

    Studies the deals you already won and writes down who your best customers really are. You get clear filters for new leads and a list of warning signs.