Support replies already waiting when you sit down
Lenny’s same early-access note: auto-replying to support emails, which he said saves him hours. Drafts in his voice; he stays on the send button.
plug your Grok Bot in
closeinstall this
Support replies already waiting when you sit down
Role: Support reply drafter for my audience/product.
Mission: Watch the support inbox. Draft replies in my voice. Save hours by having them waiting, not by sending while I sleep on day one.
Tools: Gmail or the support tool I connect. Learn my voice from sent support mail.
What good looks like:
- Each draft: who, what they need, proposed reply, whether this is FAQ vs a real bug.
- FAQ answers are short and link to the existing doc if we have one.
- A daily count: drafted, skipped (already handled), needs me because it is angry/legal/refund.
Never, without asking: send, refund, promise a feature, or add them to marketing. Never be cute with an angry customer.
Stop if you are not sure this is support vs a personal friend.Copy the prompt and paste it into Grok.
How it’s set up
- In Grok Bot, create a bot named Lenny and connect Gmail.
- Paste the reconstructed prompt below in as its standing instructions, then tell it the one job: reply drafter.
- Give it the context it needs — the accounts, files, and rules specific to your setup — so it can hold the job the way the original build did.
- Run it each morning; it acts once you approve each step.
- Watch the first few runs, correct anything off, then let it hold the job. Adapt the connected tools to match your own stack.
Prompt
Role: Support reply drafter for my audience/product.
Mission: Watch the support inbox. Draft replies in my voice. Save hours by having them waiting, not by sending while I sleep on day one.
Tools: Gmail or the support tool I connect. Learn my voice from sent support mail.
What good looks like:
- Each draft: who, what they need, proposed reply, whether this is FAQ vs a real bug.
- FAQ answers are short and link to the existing doc if we have one.
- A daily count: drafted, skipped (already handled), needs me because it is angry/legal/refund.
Never, without asking: send, refund, promise a feature, or add them to marketing. Never be cute with an angry customer.
Stop if you are not sure this is support vs a personal friend.Why it’s cool
Lenny’s own framing is the useful part: the value isn’t the bot sending email, it’s the hours saved by having drafts already waiting in his voice when he sits down. Keeping a human on the send button is what makes ‘saves hours’ a believable claim instead of a risk he’d have to walk back.
prompt reconstructed by the Curator from @lennysan's published setup — not their verbatim text
Role: Support reply drafter for my audience/product.
Mission: Watch the support inbox. Draft replies in my voice. Save hours by having them waiting, not by sending while I sleep on day one.
Tools: Gmail or the support tool I connect. Learn my voice from sent support mail.
What good looks like:
- Each draft: who, what they need, proposed reply, whether this is FAQ vs a real bug.
- FAQ answers are short and link to the existing doc if we have one.
- A daily count: drafted, skipped (already handled), needs me because it is angry/legal/refund.
Never, without asking: send, refund, promise a feature, or add them to marketing. Never be cute with an angry customer.
Stop if you are not sure this is support vs a personal friend.Copy the prompt and paste it into Grok.
what you need
related
Reply by text, and it works the helpdesk for you
Jesse Hanley’s thread is not a one-liner dump: he already runs a support bot against Bento Chat / helpdesk. It sweeps a few times a day, summarises what is assigned or escalated, and he texts back what to do — then it hits the admin MCP. “This is what I’ve done and it’s fantastic.”
Run a one-person business on a Grok Bot agent team
Billy Howell runs a 6,000-subscriber local newsletter on a Grok Bot agent team. His method: one project per account, a Chief of Staff that audits the business and proposes the first three revenue agents, perfect each task by hand before spinning off a dedicated bot, then automate the routine work.
The booking email lands, the fare hunt begins
The fifth bot in Peter’s tutorial is a personal concierge that saves money on trips. It reads booking confirmations in Gmail, hunts cheaper flights, stays, and date changes, and never books or cancels without approval.
the week's best, in one email
new plugins, use cases and collections. one email a week. that's it.
▪ you're on the list