Online stores

AI agent for Shopify enquiries on WhatsApp

An AI agent helps customers choose a Shopify product and understand purchase terms on WhatsApp, using the steps supported by the connection.

Explore the AI agent on other channels

The customer context

Can I get one green mug and one white mug?

The customer may know a product but still need to compare size or color. Telp uses the connected source and keeps the purchase boundary explicit.

What remains after the conversation

The AI agent created a cart with the selected product and variant. The customer completes checkout and payment in the Shopify store; the order is not confirmed yet.

Your store WhatsApp
  1. Customer

    Can I get one green mug and one white mug?

  2. Telp

    Both colours are available at 900 RSD each, 1,800 RSD in total. Shall I create that cart?

  3. Customer

    Yes, one green and one white mug.

  4. Telp

    I have created the cart with one green mug and one white mug, 1,800 RSD in total. Complete the purchase and payment in the store.

From a question to the next step

  1. 01

    The customer starts a WhatsApp conversation.

  2. 02

    Telp checks catalog details.

  3. 03

    The verified connection determines the continuation to purchase.

Clarify bundles and quantities before the customer pays

A WhatsApp customer may request several products, different sizes or a combination of accessories. The AI agent separates the items and asks questions that prevent an incorrect choice. Bundle explanations use the available offering within the connected WhatsApp conversation.

Agreement about products is not confirmation of payment. Shopify catalog reading, supported purchase actions and WhatsApp communication rules are checked separately. The customer should review selected items and complete the appropriate purchase flow, as described in the Shopify integration with a Telp AI agent.

The customer mixes several variants in one message

The agent clarifies which model, size and quantity belong to each item. It does not treat an ambiguous list as a completed order.

The customer says they have already paid

A statement in a message is not proof of payment. Confirmation relies on an available authorized flow or a team check, not the agent's assumption.

An AI agent across channels

Shopify customers ask in more than one place

Questions about your Shopify range can arrive on Instagram, Messenger, WhatsApp, Viber, Telegram or your website. The AI agent uses the data it can access; the next purchase step depends on the channel and connection. A phone agent collects an enquiry for your team, not a completed Shopify checkout.

Each channel needs its own connection and verification. Catalog access does not automatically enable ordering or payment on every channel; available actions and confirmations depend on the configured flow.

FAQ

Frequently asked questions

Is a product selection already an order?

No. The customer still needs to complete the supported purchase and payment steps.

Can the AI agent help with a bundle containing several products?

It can clarify items and explain bundles listed in the catalog. It does not create a new commercial offer or discount without approved rules.

Does sending a purchase link confirm an order?

No. A link or an item selection confirms neither an order nor payment. The customer must complete the appropriate steps in a supported flow.

Can the agent check whether an accessory is included in the price?

It can use the available bundle description and price. If the source does not list the accessory as included, the agent requests a check rather than promising it.

Does WhatsApp have separate communication requirements?

Yes. Channel connection, communication rules and any costs are checked separately from the Shopify catalog and purchase flow.

Can the same catalog support questions on the site and in messages?

Yes, with the appropriate connection for each channel. That does not mean every purchase action is available everywhere.

Want to validate this workflow with your own examples?

Tell us the channel, current process and first result you want to improve. We will suggest a focused rollout path and the cases your team should test.