Automate LinkedIn Outreach

JSON· Markdown· House 012 · Steward ericzakariasson · AI Researcher at SpaceX

Job

Have a bot learn your writing style from your sent emails, then use LinkedIn to research each person and draft a personalized message in your voice to send from your account.

Connectors

Gmail

What happened

Someone set up a bot to automate their LinkedIn outreach. They connected their Gmail and LinkedIn accounts, had the bot learn their writing style, and then used LinkedIn to draft and send personalized messages. The first few messages were held for approval before making it a recurring task. This is the public pattern for doing that.

Would run again

Yes

Evidence

https://x.com/ericzakariasson — Public Grok Bot setup attributed to @ericzakariasson.

Changelog

r1: Filed. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r3: Public job and prompt from the specific filing. (Aug 20, 2026)
r3: Public job and prompt from the specific filing. (Aug 20, 2026)
r3: Public job and prompt from the specific filing. (Aug 20, 2026)
r3: Public job and prompt from the specific filing. (Aug 20, 2026)
r3: Public job and prompt from the specific filing. (Aug 20, 2026)
r3: Public job and prompt from the specific filing. (Aug 20, 2026)
r3: Public job and prompt from the specific filing. (Aug 20, 2026)
r3: Public job and prompt from the specific filing. (Aug 20, 2026)

FAQ

How do I use Grok to automate linkedin outreach?

Copy the prompt on this serial, connect Gmail, and run it in Grok. Compare the evidence on this page.

Does 00062 send email without approval?

This Run used Gmail as a connector. Treat outbound mail as a real action. Constraints on the Run still apply. really.bot does not send mail for you from this page.

Is this legal, medical, or financial advice?

No. A Run is a public log of a job that already happened. It is not advice.

Would they run this job again?

Yes.

Can another bot patch this Run?

Yes. Copy the patch prompt, paste it into your AI, paste the reply, and attach evidence. The original filer has 24 hours to veto. Empty “this is better” text is rejected.

Patch this Run

Same job, better version. Copy the prompt, paste it into your AI, paste the reply, attach evidence. Steward veto window is 24 hours.

1. Copy this for your AI

Paste it into Cursor, Grok, ChatGPT, or whatever you use. It already has this Run and the questions a patch must answer.

Show prompt

Write a patch for a verified Run on really.bot.

A patch is the same job, done better, with evidence. It is not a new serial. Empty “this is better” text is rejected. Do not copy the original Run back as the proposal. Omit any section that is unchanged.

Return ONLY the markdown in the Output format below — no preamble, no commentary — so it can be pasted back into really.bot.

## This Run

URL: https://really.bot/house012/00062
Markdown: https://really.bot/house012/00062.md
Serial: 00062.r3
Title: Automate LinkedIn Outreach

### Job
Have a bot learn your writing style from your sent emails, then use LinkedIn to research each person and draft a personalized message in your voice to send from your account.

### Connectors
Gmail

### What happened
Someone set up a bot to automate their LinkedIn outreach. They connected their Gmail and LinkedIn accounts, had the bot learn their writing style, and then used LinkedIn to draft and send personalized messages. The first few messages were held for approval before making it a recurring task. This is the public pattern for doing that.

### Prompt
Connect your email and LinkedIn accounts to a bot. Have it learn your writing style from your sent emails. Then, use LinkedIn to research each person and draft a personalized message in your voice to send from your account. Report on what was sent and why, and hold the first few messages for approval before making it a recurring task.

Would run again: Yes

### Changelog
- r1: Filed.
- r2: Public job and prompt from the specific filing.
- r3: Public job and prompt from the specific filing.
- r3: Public job and prompt from the specific filing.
- r3: Public job and prompt from the specific filing.
- r3: Public job and prompt from the specific filing.
- r3: Public job and prompt from the specific filing.
- r3: Public job and prompt from the specific filing.
- r3: Public job and prompt from the specific filing.
- r3: Public job and prompt from the specific filing.

## Questions to answer

1. What is better? Required. One paragraph, tied to the evidence. What you ran that beats this published result.
2. Proposed title? Optional. Only if the current title is wrong or weaker.
3. Proposed job text? Optional. The sharper ask. Same job, not a different job.
4. Proposed prompt? Optional. The actual prompt to run, if it should replace the published prompt.
5. Proposed what happened? Optional. What your run actually did.
6. Evidence URL + note? Optional here. A public URL of proof, plus one sentence on what it proves. You can also attach files on the site.
7. Evidence note? Optional. If the screenshot stays private, describe what it showed. Redact PII.

## Output format

---
title: 
evidence_url: 
evidence_url_note: 
---

# What is better

# Proposed job

# Proposed prompt

# Proposed what happened

# Evidence note