# An AI shopping assistant that runs on the shopper's own AI

Source: https://tensorpass.app/use-cases/ecommerce
Published on 2026-11-12, updated on 2026-11-15.

> How a store answers product questions with each shopper's own AI, which MCP tools it serves, which interface it picks and how checkout stays on its pages.

Traffic from AI assistants to US retail sites is forecast to grow 130% over the 2026 holiday season, and 159% on Thanksgiving. Of the shoppers who used AI to shop online, 77% feel more confident in their purchase and 69% are less likely to return it. **AI Connect**, the TensorPass SDK a website installs, puts that assistant on the store's own pages. The shopper's model reads the catalog through the store's tools and answers on the shopper's own account through [AI Wallet](/glossary/ai-wallet), so the store pays no [inference](/glossary/inference-cost).

## Questions shoppers bring to an AI [#questions-shoppers-bring-to-an-ai]

Amazon's **Rufus**, its shopping assistant, served more than 300 million customers in 2025 and delivered nearly $12 billion of incremental annualized sales. AI and agents influenced 20% of global Cyber Week orders in 2025, worth $67 billion, and retailers running their own agents grew sales 32% faster. On Shopify, traffic from AI assistants grew 8 times in the first quarter of 2026, and orders from AI searches grew nearly 13 times.

Each question below maps to a tool call on the store's server:

- "Which running shoes in the sale fit a wide foot under $120?" calls `search_products` with the shopper's words.
- "Is the blue one in stock in size 9?" calls `get_product` and reads the stock of each variant.
- "What separates these two kettles?" calls `get_product` twice and compares the answers.
- "Which collection has gifts for a ten year old?" calls `list_collections`.

Searches run on Shopify's own catalog data convert at twice the rate of searches run on scraped data. An assistant on the store reads that same catalog data through its tools.

## Catalog tools served over MCP [#catalog-tools-served-over-mcp]

The **Model Context Protocol** ([MCP](/glossary/model-context-protocol)) is the open standard through which a model calls a site's tools. The AI Connect Shopify app serves three read only tools on the store's own domain, at the app proxy path `/apps/aiconnect/mcp`, and reads the store through the Storefront API.

| Tool | What it returns | Question it serves |
| --- | --- | --- |
| `search_products` | The matching products, each with its handle, title, price range, stock and page address | "Running shoes under $120" |
| `get_product` | One product in full: description, options, each variant with its price and stock, collections | "Is the blue one in stock in size 9?" |
| `list_collections` | The store's collections, each with a summary and its page address | "Gifts for a ten year old" |

A store on its own stack writes the tools its catalog needs. A `list_categories` tool returns the categories, sizes and price bands the catalog accepts, and the model then fills each filter with a value the catalog holds. The [MCP guide](/docs/guides/mcp-tools) sets the design rules: a verb and a noun for each name, every enum value explained, every input bounded, and the page address returned with each result.

## Which interface suits a store? [#which-interface-suits-a-store]

The SDK ships five ready made interfaces, described under [interface modules](/docs/modules). Four of them suit a store:

- **Popup** (`AiChatPopup`): a round button in the corner of the page opens the chat. It is the default form of the Shopify app embed.
- **Side panel** (`AiChatPanel`): the chat docks at the edge of the page and keeps the conversation while the shopper opens a suggested product.
- **Search bar** (`AiSearch`): the store's search box answers in a card under the bar and shows the store's own product cards through `renderToolResults`.
- **Inline chat** (`AiChatInline`): a chat card set in a "find your size" section of a product page.

## Checkout on the store's own pages [#checkout-on-the-stores-own-pages]

The Shopify app's tools read the catalog, and the cart and the payment run in the store's own checkout. Each product in the answer links to the page address its tool returned. The **answer guard** of the SDK lets a link through when it points to the page's own origin, to a host the store lists, or to an address a tool returned as a field. A shopper who clicks lands on the store's product page.

In March 2026 OpenAI scaled back Instant Checkout, and buyers who find a product in ChatGPT now check out on the merchant's own store. Shopify moved its catalog and cart tools to `/api/ucp/mcp`, and its Storefront Catalog MCP there expects an agent profile in the arguments of every call. The shopper's model has no way to add that profile, and the AI Connect app serves its own three tools for that reason.

A store whose tools return product reviews passes third party text to the model. The SDK closes every tool result in an envelope sealed with a random salt drawn for each conversation, and instructions planted in a review stay inside it as data. This is the guard against [prompt injection](/glossary/prompt-injection). The app's admin page holds the store's [guards](/docs/modules/guards) for the catalog: up to 50 patterns of names and content the merchant keeps out of the chat.

## Next steps for a store [#next-steps-for-a-store]

- **Shopify**: the [Shopify quickstart](/docs/quickstart/shopify) covers the app embed and the catalog server. The app is not on the Shopify App Store yet. Its code is in the AI Connect repository, and on 11 November 2026 it answered a real question from the catalog of a development store.
- **Own stack**: the [React](/docs/quickstart/react) or [Next.js](/docs/quickstart/nextjs) quickstart, then the MCP guide.
- **Done for you**: the [AI native service](/ai-native) audits the store, serves its catalog as an MCP server, adds an AI mode in the store's design system and hands over the code, in under 24 hours. The result is an [AI native website](/glossary/ai-native-website).

On 16 November 2026 the SDK packages of version 0.1.0 are on npm, and AI Wallet waits on the Chrome Web Store's review while a visitor can install it by hand from https://tensorpass.app/wallet. A shopper without AI Wallet gets the assistant through a sign in with OpenRouter, or with the TensorPass plan on a site that passes a site key.

## Sources [#sources]

- [Adobe, US holiday shopping season to hit record, 28 September 2026](https://news.adobe.com/news/2026/09/adobe-us-holiday-shopping-season-to-hit-record)
- [Amazon.com, Inc., Exhibit 99.1 to Form 8-K, fourth quarter and full year 2025 results, 5 February 2026](https://www.sec.gov/Archives/edgar/data/1018724/000101872426000002/amzn-20251231xex991.htm)
- [Salesforce, Cyber Week results on AI and agents, 5 December 2025](https://www.salesforce.com/in/news/press-releases/2025/12/05/cyber-week-ai-agents-sales/)
- [PYMNTS, AI drove orders at Shopify up 13 times in Q1, 5 May 2026](https://www.pymnts.com/earnings/2026/ai-drove-orders-shopify-up-13-times-q1/)
- [Modern Retail, Shopify says purchases are coming inside ChatGPT through agentic storefronts as OpenAI retreats on Instant Checkout, 12 March 2026](https://www.modernretail.co/technology/shopify-says-purchases-are-coming-inside-chatgpt-through-agentic-storefronts-as-openai-retreats-on-instant-checkout/)
- [Shopify, Storefront MCP servers, undated](https://shopify.dev/docs/apps/build/storefront-mcp/servers/storefront)
- [TensorPass, Shopify quickstart, 12 November 2026](/docs/quickstart/shopify)
- [TensorPass, Guards, 12 November 2026](/docs/modules/guards)

## Questions

**Who pays for the answers of the shopping assistant?**
Each answer runs on the shopper's own ChatGPT, Claude or Gemini account through AI Wallet and counts against that account's plan or credits. The store pays for its MCP server and its hosting.

**Does the assistant place orders or take payments?**
The three tools of the AI Connect Shopify app read the catalog and change nothing. The answer links each product to its page on the store, and the shopper adds it to the cart and pays in the store's own checkout.

**What does a shopper need to use the assistant?**
Chrome with the AI Wallet extension and one AI account connected in it. On 12 November 2026 the wallet loads unpacked and its Chrome Web Store item is a draft that has not been submitted.

**Does the shopper's AI provider see the whole catalog?**
The provider receives the conversation, which holds the tool results of that conversation and nothing else. The catalog stays on the store's server, and the model reads only what search_products, get_product and list_collections return.