AI agent

An AI agent that knows when to stop

The dangerous thing is not an AI that cannot answer. It is one that answers confidently and wrongly.

Rima AkterAI active
Dhaka er baire delivery koto din lage? Ar COD ache?

10:02

AI Assistant

Dhaka-r baire 3–5 din lage, delivery charge 120 taka. Ji, sara desh-e cash on delivery ache.

10:02

Size na hole return korte parbo?

10:04

AI Assistant

Ji parben — 7 diner moddhe, tag lagano thakle. Amader team pickup kore nibe, apnar kono charge lagbe na.

10:04

Both answers came out of your knowledge base — the delivery page and the returns policy. Nothing here was invented.

The problem

A generic chatbot invents delivery charges and return policies. One wrong answer costs you a customer and a refund, and you find out days later.

How ReplyX handles it

Grounded in your knowledge only

The AI answers from what you wrote down. If your knowledge base doesn't cover it, it says so and calls a human instead of guessing.

A confidence threshold you set

Every answer carries a confidence score. Below your threshold, the conversation goes to a person — you decide how cautious it is.

Escalation words that always win

List the phrases that mean 'get me a human'. When a customer uses one, the AI hands over immediately without trying to answer.

Honest outside business hours

Set your hours and the AI tells customers when your team will actually be back, instead of leaving them waiting on a reply that comes tomorrow.

What you get

Everything below is built and live today — not a roadmap.

  • A separate agent per product or service, each with its own knowledge
  • Your own tone, greeting and handoff message
  • Forbidden topics the AI will never engage with
  • Test playground that shows which sources an answer came from
  • Per-conversation cost, so AI spend is never a surprise

Ask it anything, first

It answers — and tells you where the answer came from

Before it ever meets a customer. No conversation is created; it runs against the same knowledge a real reply would use.

Test your AI

Ask a question the way a customer would. It runs against that agent's knowledge without creating a real conversation.

Rupa Assistant ▾Dhaka er baire delivery koto din lage?Test
AI answeredUsed knowledge baseConfidence 92

Outside Dhaka usually takes 3–5 days. Delivery is 120 BDT, and cash on delivery is available nationwide.

Answered from

Delivery & Returnsrupascloset.com/faq

Before it ever meets a customer, you can ask it anything and watch what happens. Nothing is created, no conversation is opened — it just runs against the same knowledge a real reply would use.

The answer never arrives alone. It comes with a confidence score, and with the names of the sources it was built from — so when a reply is wrong, you are not guessing at a black box. You open the source that fed it and fix the sentence that was wrong.

That is the difference between an AI you can correct and one you can only switch off.

And when it cannot

It stops, and says why it stopped

The dangerous chatbot is not the one that fails. It is the one that sounds certain and is wrong.

The dangerous chatbot is not the one that fails. It is the one that invents a refund policy, sounds certain, and you find out four days later from an angry customer.

So the threshold is yours to set, and the score is shown against it rather than hidden. Below the line the reply is never sent — the conversation goes to a person with the whole thread and the reason attached, and if you use round-robin or least-busy handover it already has an owner who already has a notification.

Every handover is counted by its cause — knowledge gap, low confidence, asked for a person, quota, outage. A handoff rate you can read is a handoff rate you can lower, and this one names the sentence you need to write.

Test your AI
Rupa Assistant ▾Six days late — can I get a full refund?Test
Would hand off to humanConfidence 41

I am not able to confirm a refund for a late delivery — let me get someone from the team to help you with this.

Against your threshold

41 of 70 needed

Your refund policy does not cover a late delivery, so nothing in the knowledge base could carry this answer.

Needs humanAssigned to Sadia · she has been notified

What you hold it to

Yours to instruct, and yours to restrain

An agent that answers customers in your name should be something you can read, edit and rein in.

It speaks as you, not as a bot

A name, a language and a tone you choose. Bangla, English, or whichever the customer wrote in.

It stays off subjects you name

Medical advice, a competitor's pricing, anything you would not want an untrained new hire answering.

One agent per brand, if you need it

Several products under one team, each with its own knowledge and its own persona, answering on its own channels.

You can read what it was told

The instructions it runs on are yours to see and edit — there is no hidden prompt doing something else.

AI agent — Rupa's Closet

Rupa Assistant

Answers in Bangla and English · friendly

Answer only above

70

Below this it hands over instead of guessing.

Hand over immediately on

refundcomplaintmanagerspeak to someone

Never discusses

medical advicecompetitor pricinglegal opinions

Answers from

Delivery & Returns · Payment & bKash · rupascloset.com/faq — and nothing else.

Try it on your own questions

Add your FAQ, connect one channel, and see how much the AI handles before you pay anything.

No card required · Free plan forever · Set up in minutes