Guide
Hermes Agent: use cases for small business
Hermes Agent is an open-source AI agent from Nous Research. It can live in your messaging apps, remember projects across sessions, run scheduled jobs, browse the web, and spawn subagents — not just chat. The hard part isn't installing it. It's knowing which business jobs to hand it first, and which ones stay on approval. The software is free under the MIT license; you still pay for the model provider (and any hosting) you choose. Start with a morning brief, inbox drafts, lead follow-ups and FAQ answers from your own docs. Keep sends and money on approval. Features and credit tiers change — check Nous's pages before you budget.
What to hand to an agent first
A weekday morning brief
Summarise yesterday's unfinished items, today's calendar, and anything that needs a human decision — delivered to Slack, Telegram or email on a schedule. Keep it read-and-report until the brief is consistently useful.
Inbox triage with drafted replies
Sort new mail into reply / FYI / ignore and draft replies in your voice. Nothing sends until you approve. Prompt injection in email is a real risk, so draft mode is non-negotiable at the start.
Lead and quote follow-ups
Quiet leads and unsigned quotes get a next-step draft that references the last conversation. You approve every send for the first weeks.
FAQ answers from your own docs
Point it at a short FAQ or help doc you wrote. Anything outside that list hands off to you.
Recurring ops reports
Weekly checks, pipeline summaries, stock alerts, or what's-overdue cron jobs. You still read the output before acting on money or customers.
Meeting and client prep
Research a prospect or client, pull past notes, and draft a prep brief. Treat it as a shortlist to check, not a decision.
Not sure which jobs fit your business?
Build my free AI plan →Ready-made use cases
- 01CEO morning brief in 5 minutes
One message each morning: calendar, urgent emails, money in/out, and the 3 things that move the business today.
~3h/week · estimate - 02Inbox triage with drafted replies
The agent sorts your inbox into reply / FYI / ignore and drafts replies in your voice for you to approve.
~5h/week · estimate - 03Never miss a lead follow-up
The agent checks your CRM or inbox for leads that went quiet and drafts the next follow-up.
~4h/week · estimate - 0424/7 FAQ support in your voice
The agent answers common customer questions from your docs and hands off anything tricky.
~8h/week · estimate - 05Invoice chaser that gets you paid
The agent tracks unpaid invoices and sends polite, escalating reminders.
~2h/week · estimate
Example: Grok Bot setup
Grok Bot routine: CEO morning brief in 5 minutes Schedule: Daily 7:30 Every morning, read my calendar for today, my unread emails from the last 24h and yesterday's revenue. Send me a brief: (1) meetings with one prep note each, (2) emails that need my reply with a suggested one-line answer, (3) money in/out, (4) the 3 highest-leverage tasks for today. Keep it under 200 words. Rules: draft first, never send or post anything external without my approval. Keep summaries short.
Grok Bot, ChatGPT, Claude and n8n versions: all templates
Keep these human
- Payments, refunds, invoices to clients and ad spend: drafts only until you trust the routine.
- Email, SMS, WhatsApp, public posts and review replies: read before anything goes in your name.
- Don't paste passwords, 2FA codes or card numbers into prompts. Prefer a dedicated agent mailbox when you can.
- Deletes, price changes, mass sends and data wipes stay with you.
- Start in draft mode: the agent prepares, you approve, then you loosen the leash routine by routine.
FAQ
What should an AI agent do first for Hermes Agent?
A weekday morning brief: Summarise yesterday's unfinished items, today's calendar, and anything that needs a human decision — delivered to Slack, Telegram or email on a schedule. Keep it read-and-report until the brief is consistently useful. Inbox triage with drafted replies: Sort new mail into reply / FYI / ignore and draft replies in your voice. Nothing sends until you approve. Prompt injection in email is a real risk, so draft mode is non-negotiable at the start. Lead and quote follow-ups: Quiet leads and unsigned quotes get a next-step draft that references the last conversation. You approve every send for the first weeks.
What should stay human?
Payments, refunds, invoices to clients and ad spend: drafts only until you trust the routine. Email, SMS, WhatsApp, public posts and review replies: read before anything goes in your name. Don't paste passwords, 2FA codes or card numbers into prompts. Prefer a dedicated agent mailbox when you can. Deletes, price changes, mass sends and data wipes stay with you. Start in draft mode: the agent prepares, you approve, then you loosen the leash routine by routine.
Is there a ready-made template?
Yes. Start with "CEO morning brief in 5 minutes": copy-ready Grok Bot, ChatGPT, Claude and n8n templates are at https://whatshouldmybotdo.com/use-cases/ceo-morning-brief#templates.