Draft personalized outbound, recaps and forecasts for sales
Cursor's internal ChatGTM drafts signal-based outbound messages with personalized landing pages, call recap emails and follow-ups, and assembles the deal forecast.
Done withCursor
- What they did
- ChatGTM sits on top of Salesforce, Gong, the data warehouse, LinkedIn and other sources, and pulls context live rather than from a stored repo. Each morning it drafts about 25 signal-based outbound messages, each with a landing page matched to the contact's stack and role. It also drafts call recaps and follow-ups, and before Thursday forecasts it scans every deal to assemble the forecast. Reps review and send through Gmail or Outreach.
- How it went
- A pilot group of 8 SDRs booked triple the qualified meetings, with the top two at 4x. Sales leaders also report AE ramp time down by more than 50%. These are the author's reported figures, from about 1.5 months of use.
- Worth knowing
- The core build took about two months with three people, on top of earlier failed attempts. George Hou says most GTM teams shouldn't build this, and he warns that long-running agent research gets slow and costly.
Try it yourself with Cursor
Using my notes on [prospect or account list] and these recent signals [news, hiring, product usage], draft a short personalized outbound email for each contact and a simple landing page outline tailored to each. Also write a call recap email for [call notes path] with follow-up steps. Give me all drafts in one file and do not send anything.
Source: thesignal.club · Undated
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Keep coding agents running autonomously for long stretches
Cursor's write-up on scaling long-running autonomous coding.
Run a scheduled personal assistant that builds a task dashboard
A Rippling engineer's Cursor cron agent runs every two hours, reading Slack notes, GitHub PRs, Jira issues and mentions, deduplicating them and posting a dashboard.
Migrate 180 microservices to a new framework version
Brex built Cursor-based self-correcting agents that let one engineer migrate 180 microservices to a newer Micronaut version in about a month.
- Custom agent
Sell services through an agent that takes payment and delivers
An agent runs a transaction flow, creates Stripe checkout links, verifies payment before delivering a service, and asks the owner on Telegram to approve refunds or disputes.
Review Meta ad performance inside Ads Manager
An agency tested Manus on a real ecommerce client's Meta ads account; it reported a 14.25x ROAS against an actual 1.76x and corrected itself only when challenged.
- Claude
Run a Monday competitor-monitoring brief from job listings
Claude is set up as an agent that browses competitors and reads their job listings every Monday morning to infer what they may do next.