The task
Closed-won deals already hold useful context: the pain points, the objections, and the traits of accounts that buy. The source says this knowledge is rarely turned into outreach to similar companies. The builder wanted a routine that does it every week and leaves the first drafts to an AI assistant.
What they did
The builder connected HubSpot, Clay, Slack, and email to Claude Cowork through the official connectors and built the task piece by piece. It begins in HubSpot, with deals that were newly marked closed-won. According to the source, each weekly run looks at the last 7 days of deals and pulls call transcripts that were recorded in Sybill, which already fills structured CRM fields such as situation and pain. The task then chooses lookalike companies from the traits of those deals and the builder's ideal customer profile. According to the source, it names 10 lookalike companies, looks up 3–5 contacts at each in Clay, and writes a 4-email sequence with LinkedIn messages for every contact. The drafts are delivered to Slack. Before building, the builder wrote reusable skills for the ideal customer profile, personas, messaging, and product information.
What the source reports
According to the source, the drafts are very close to sendable each time, because the call records already carry structured fields. The source gives no figures for time saved, replies, or revenue.
Where the approval sits
The task only drafts. It posts the drafts to Slack, and the team reviews them there. According to the source, the builder has not automated outbound sending and keeps a person in the loop on purpose.
Worth knowing
The source is one section of a newsletter edition that profiles several marketers' builds, and the newsletter itself describes this one. It shows the setup but no outcomes. The task is prospecting to new accounts rather than follow-up on existing conversations, so it fits this category loosely. The source says outbound sending is not automated yet.
Source: newsletter.mkt1.co · Mar 2026
Drafted with AI assistance and checked automatically. A person is responsible for the collection. How these entries are made
Prompt for your agent
Find lookalike companies and draft first notes
Find companies that resemble your best recent customers and draft a short first outreach note for each, ready for your review.
More in this category
- Sales follow-ups
A builder's follow-up agent saves Gmail drafts and asks for approval in Slack
An automation builder runs a scheduled agent that reads leads in Airtable, checks Gmail for replies, and saves follow-up drafts. The drafts go to Slack, where the builder approves or rejects each one.
Read the entry - Sales follow-ups
A sales team has an agent draft post-call emails, and reps edit and send them
A sales team uses an AI agent to draft the follow-up email after each sales call, based on the call summary. The rep edits every draft and sends it personally.
Read the entry
Ninety minutes live on your tools. One automation running before we hang up.