Live demo · Support Agent

Live AI customer support demo: resolve a real ticket in chat.

Chat with an AI support agent for a fictional online store. It answers from the help center with sources, checks your identity before it touches an order, starts returns and refunds, and asks a person to approve anything over its limit. Every step is in the trace.

  • You play a customer of an online homeware store
  • Fictional business, sample data, sandboxed tools
  • Every step shown, with the agent's reason

Kettle & Pine

Fictional homeware store · support chat

Live · sandbox
  1. Hi! I'm Kettle & Pine's AI support assistant. I can answer questions about orders, delivery and returns, and sort most problems right here. What can I help with?

Live AI · fictional business · don't share real personal data · how demo chats are handled

Put it to the test

Things to try.

Try this

  • Use order 1042 (alex@example.com), 1057 (sam@example.com) or 1063 (jo@example.com). Try a wrong email: it will not reveal the order.
  • Ask for a refund of more than $50: it waits for a team member, and you play the team member.
  • Ask something the help center does not cover: it should say so instead of guessing.
  • Ask for a person at any time.

Guardrails in this demo

  • Answers policies only from the help center, with sources
  • Order number and email must match before it shows anything
  • Refunds over $50 need a person’s approval
  • Cannot refund more than the order total
  • Hands off to a person with a summary

The rules live in the tools, in code. The model can't talk its way past them, which is why a prompt injection doesn't get far.

Under the hood

What happens when you send a message.

  1. 01

    Checked before the model sees it

    A one-time Cloudflare human check, rate limits, a length cap, card numbers and keys removed, and Llama Prompt Guard scoring the message for prompt injection.

  2. 02

    The agent picks its tools

    A large language model reads the conversation and decides which of its allow-listed tools to call: calendar, orders, catalog, CRM or documents. It must give a reason for each call.

  3. 03

    Rules run in code

    Each tool checks its own rules (identity, limits, stock, access rights) on fictional sample data. Anything over a limit stops at an approval gate for a person.

  4. 04

    Checked on the way out

    The reply is screened for leaked instructions before you see it, and every step lands in the trace beside the conversation.

For your business

The Support Agent, on your systems.

Resolves tier-1 tickets across chat, email and WhatsApp.

  • From $2,500 + $449/mo
  • Live in about 2 weeks
  • Connects to Zendesk, Freshdesk, Intercom, HubSpot Service Hub, Gorgias and more

FAQ

About this demo.

Is this support agent demo real AI or a recording?

It is real. Every reply comes live from a large language model (by default the open-weight gpt-oss-120b, served by Groq or Cerebras, with Google Gemini as a backup) that decides which tools to call. The business, its calendar, orders and documents are fictional sample data, so you can try anything without consequences.

What happens to what I type?

It is sent to our server and an AI provider (Groq, or a backup such as Cerebras or Google Gemini) to generate the reply, and a short log of each turn is kept by our host for a few days to stop abuse and improve the demos. It is not used to train models. Please use made-up details: this is a sandbox. See the privacy policy.

Why do some actions wait for approval?

Because that is how we build agents for real businesses: the agent handles the routine work, and anything risky (a big refund, a discount, an exception to a rule) waits for a person. In this demo, you are a support team lead, so you decide.

Can I try to break it?

Please do. Ask it to ignore its instructions, reveal its prompt or bend a rule. The trace shows the guardrails at work: the injection classifier, the tools that refuse, and the output check.

What would the Support Agent look like in my business?

The same agent, connected to your real systems (Zendesk, Freshdesk, Intercom, HubSpot Service Hub and more), trained on your own information and rules, with your approval gates. Live in about 2 weeks, from $2,500 + $449/mo. See the Support Agent page for what is included.

More live demos

Try another agent.

Want one that works on your data?

Book a free 30-minute call. We'll map the agent to your systems and rules, and quote a fixed price within 24 hours.

NDA on request from the first call · You own 100% of the code and IP

Before you go

What would your project cost?

Answer a few questions and get a price range, a timeline and what drives the cost. Two minutes, no email needed.

Estimate my projectOr start with the AI Opportunity Audit, $490

Visionbotix

AI concierge · answers from this website

Live · sandbox
  1. Hi! I'm Visionbotix's AI concierge. Ask me what we build, what it costs, or which agent fits your business. I answer from this website and can set up a call with the team.

Live AI · fictional business · don't share real personal data · how demo chats are handled