Grok Bot · xAI
Run a daily SDR routine that flags risky contacts before outreach
An SDR at SpaceXSI describes a set of Grok Bots, working alongside Cursor agents, that run his morning prospecting, keep the contact sheet and CRM sequences in order, and sort every contact into safe or needs review before anything goes out.
What they did
Cursor cloud agents build account packets from product usage, closed-lost deals and past conversations, and draft first-touch emails that open with an account-specific signal. Named Grok Bots handle the rest: one runs the morning process and fixes sequences, one maintains the prospecting sheet, one prepares LinkedIn requests, and one creates Salesforce records and sequence changes when the normal path breaks. Each contact is tagged CLEAR (safe to enroll, unsent) or FLAG (needs a human), and the rep sends from his sequencing tool himself.
How it went
The author says one batch skipped six contacts already active elsewhere, flagged 34 for review and cleared one, and that a backlog of 24 contacts sitting in the wrong sequence was fixed in one pass, with first calls booked for the next afternoon.
Worth knowing
This is a guide on the vendor's own site, and it reports no pipeline, meeting or revenue figures. Research and drafting are done by Cursor agents, so results depend on both tools, and nothing auto-sends.
Try it with Grok Bot
Every morning at <time>, take the new accounts in <your prospecting sheet>, check <your CRM> for anyone already being worked by a colleague and skip them. For the rest, match contacts to likely roles, attach the research notes from <your research folder>, and tag each one as clear or needs review with a one-line reason. Fix any contact sitting in the wrong sequence and list what you changed. Never send or enroll anyone yourself.
We wrote this prompt from the case. Replace the parts in angle brackets with your own details.
What this label means: Vendor says
The maker describes it on its own site or launch post. It shows what the product is meant to do, with no independent result.
Real cases of AI agents at work, from every major agent, each linked to where it was first reported. Rewritten in our own words, most with a prompt you can try. These are not Wize customers.