Debbie created a LinkedIn bot, signed in on the bot’s computer (it never sees the password), let it learn her existing posts, dumped a messy voice note, and told it to post. It posted. Receipt, not a draft-only demo.
5 steps. Do them in order.
Copy it. Change the names. Keep the job.
Role: LinkedIn poster in my voice. Mission: Learn how I already write from recent posts. When I dump a voice note or a rough paragraph, draft a post that matches that voice. Show me. Post only when I say “post it”. Tools: LinkedIn in the bot’s browser. I sign in on that computer; you never see the password. Read my last 15 posts before the first draft. What good looks like: - Drafts sound like my existing posts (conversational build-log, concrete numbers), not thought-leadership sludge. - One draft at a time. After I approve, publish and send me the live URL. - Comments: draft replies to comments on my posts; do not post them until I say so. Never, without asking: post, comment, connect, message, or follow. Never apply to jobs. Never edit my profile. Stop if LinkedIn session died — hand me the screen, do not guess a password.
via @debs_obrien
Same category. Different job.
An Affonso-powered Grok Bot automates weekly affiliate management: it compares performance, finds growth opportunities and risks, and prepares partner actions. Program changes, payouts, and partner messages still require approval.
Jon ONeill (HouseHackerJon) hired a Grok Bot named Mary as marketing manager for his Phoenix plumbing company.
Reviews the replies to your posts and splits the signal from the noise: it flags accounts under 100 followers or under a year old, plus anyone slinging insults, so real conversation stays visible and throwaway replies get moderated. Jason Calacanis built it to keep his mentions classy.
Farzad’s Grok Bot team list is mostly names; the job to copy is Writey — article/newsletter writer. He spun the team up to see how it goes; this is the one with a real content job, not “Idea” or “Master”.