SMB Agents AI
← All use casesKeep customers happy

Build a 24/7 FAQ assistant from your own policies

Fewer repetitive 'what are your hours / do you take X' messages

Illustrative example — a composite of common setups, not a specific business's story.

Difficulty
Light setup
Setup time
Half a day
Monthly cost
$0-$50
Impact
Medium
ShopifyGoogle WorkspaceRetail & e-commerceRestaurants & hospitalityFitness & salons

The short version

A chatbot trained on your FAQ, policies and price list answers common website questions and hands off to a human when unsure.

What they did

A chatbot trained on your FAQ, policies and price list answers common website questions and hands off to a human when unsure. The owner started with a small pilot: one workflow, a few days of supervised use where every output was reviewed before it went out, then gradually let routine cases run with lighter oversight.

Agent/tool used: Custom GPT / website chat widget

How it went

In a typical rollout like this: fewer repetitive 'what are your hours / do you take x' messages. Most of the value comes from consistency, the task happens every time instead of when someone remembers. Expect a week or two of tuning the prompt and rules.

Worth knowing

AI drafts can be wrong or off-tone. Keep a human approving anything customer-facing at first, don't paste sensitive data (card numbers, health records, SSNs) into general chat tools, and check each tool's data and privacy terms.

Copy-paste prompt

You answer customer questions for [Business Name] using ONLY this information: [paste FAQ, policies, hours]. If the answer isn't in the information, say: 'Good question - let me get a team member to confirm' and ask for their email. Be brief and friendly.

Replace anything in [brackets] with your own details.

Step-by-step setup

  1. Write down how you handle this today, in 5-10 bullets.
  2. Connect or export data from Shopify, Google Workspace.
  3. Set up Custom GPT / website chat widget and paste in the prompt, filling in the [placeholders].
  4. Test it on 5-10 real past examples and fix anything that's off.
  5. Run it with you approving every output for one to two weeks.
  6. Once you trust it, automate the routine cases and spot-check weekly.

Published 2026-10-05. Want help setting this up?