Genspark
An all-in-one agent for slides, docs, sheets and research, which can also phone businesses for you.
- Free option: Yes
- Open source: No
- Not confirmed
Clients, bookings, calls, follow-ups.
In the real examples we've collected, people mostly use Genspark (1 example here, paid from $0, where: not confirmed), Grok Bot (1 example here, paid from $30/mo, where: not confirmed) and Hermes Agent (1 example here, paid from $0 + model costs, where: worldwide) for small business. Pick the one available where you live with the free or cheapest plan that covers it. We haven't tested agents on this job ourselves yet. Grok Bot helps run this site, so treat its count here with that in mind.
An all-in-one agent for slides, docs, sheets and research, which can also phone businesses for you.
xAI's personal agent that works on its own cloud computer and can use your email, browser and apps.
A free, open-source agent that remembers what it learns and runs on your computer or a small server.
A consultant who builds workflows for small UK businesses shared a free n8n template. It only watches one Gmail label for supplier invoices, has an AI model read each PDF into fixed fields like supplier, dates, net, VAT and total, then checks the math in plain code: net plus VAT has to match the total and the line items have to add up. Invoices that pass go into a Google Sheet, and anything that fails lands on an Exceptions tab with the reason, so a person takes a look. She notes it can't read scanned invoices and doesn't catch duplicates yet.
The poster runs Hermes Agent every day as a helper called Jarvis. They send it a one-line note about a client, and it records the date and the next step on a shared sales board. It also writes client emails, but only sends each one after the poster approves it. Logins, two-factor codes and CAPTCHAs stay with the poster.
A small business marketer tested Genspark's calling feature, which phones businesses listed on Google Maps and sends back a transcript and summary. A call asking a church about its young adults group went well. A dinner booking for 10 stalled when the host asked what time, and the reservation was never finished.
A poster in the Make Community built a scenario that picks up supplier invoices from Gmail, saves the PDF to Google Drive and reads the text with Google's OCR. Plain text rules pull out the invoice number and the purchase order number, and Make finds the matching order in a Drive folder. A Make AI Agent then compares the two line by line and marks each line as a match, a match with different wording, a mismatch or missing, with an overall status of approved, discrepancy found or escalated. The result and the agent's reasoning go into a Google Sheet. He tested it on three invoices: one matched despite different wording, one was flagged for a wrong quantity, and one was escalated because a line had no match.
A real estate photographer set up Grok Bot to check his calendar every morning for shoots two days away. It looks up the client, checks the forecast and emails a confirmation, and if rain looks likely it offers to reschedule instead. He shares his setup as a template in the post.