Magento 2 Module – Ask About Product

MAGENTO 2 · QUESTIONS · FAQ · AI ASSISTANT

Kowal Ask About Product

Combine a contact form, published FAQ, and an optional AI assistant. Use product data and your knowledge base, and turn repeated conversations into answers available to future customers.

Form and FAQ · Product context · Conversations and feedback

HOW IT WORKS IN PRACTICE

Kowal_ZapytajOProdukt is an advanced Magento 2 module for customer communication on the product page. It combines a classic question form, structured FAQ, and an AI Assistant in one cohesive solution.

In practice, this means the product page is no longer only a place to present the description and technical parameters, but becomes an active support point for customer questions. The user can:

• ask a standard question about the product,
• use ready-made answers published in the FAQ,
• chat with the AI Assistant, which answers in the context of the currently viewed product.

The module was designed to solve two problems at the same time:

• support-related, meaning it helps reduce the number of repetitive questions sent to the store team,
• product-related, meaning it builds a growing, structured knowledge base that improves answer quality over time.

In many online stores, a significant share of customer questions is repetitive:

• whether the product is compatible with a specific Magento version,
• whether it works without an additional module,
• how installation works,
• whether it supports multiple languages,
• whether it requires custom changes to the theme,
• how it behaves in a specific business scenario.

Without a dedicated support tool, these questions:

• burden support,
• slow down purchasing decisions,
• scatter knowledge across email inboxes, tickets, and sales conversations,
• do not return to the store as a structured FAQ.

This module organizes that process. First, it collects questions and answers, then organizes them into an FAQ, and in the next stage uses them as context for the AI Assistant and the retrieval layer based on OpenAI Vector Store.

The module works in layers.

A standard question submission mechanism can be enabled on the product page. The customer sends an inquiry, and the administrator or store staff receives it for further handling. This is the simplest and most predictable form of contact.

Repetitive questions and answers can be saved and published as a product FAQ. The FAQ can be displayed as a tab or as a separate section on the product page. As a result, future visitors get an answer without having to send a new question.

A lightweight AI conversation component appears above or below the standard FAQ. The user can:

• click one of the popular questions,
• enter their own question in the field Zapytaj Asystenta o ten produkt.,
• see the answer in the same conversation area.

The assistant does not work as a general store chatbot. It was designed as a product assistant, which means the answer should be based primarily on:

• the current product data,
• published FAQ,
• the current conversation history,
• optionally, retrieval results from OpenAI Vector Store.

The module provides a classic customer contact mechanism.

Key elements:

• a button or form Zapytaj o produkt on the product page,
• AJAX handling on the frontend,
• saving the question to the database,
• ability to send an email notification,
• option to enable the module globally or only for selected products.

This solution still makes sense even when the store already uses the AI Assistant. Not every question should be handled automatically. Some cases require a sales response, individual quote, or confirmation by the technical team.

The FAQ in this module is not a marketing add-on, but a structured product knowledge layer.

The administrator can:

• review saved questions,
• add answers,
• publish selected records,
• display them on the product page.

The FAQ can be shown:

• as a tab,
• as a separate section on the product page.

Importantly, the FAQ is not only for the frontend. Published questions and answers are also used as one of the most important context elements for the AI Assistant.

The AI Assistant is the central element of the module extension.

The component is embedded on the product page, by default below the gallery, and was prepared to:

• work lightweight on the frontend,
• avoid unnecessarily slowing down the first page render,
• be readable on desktop and mobile,
• be suitable for further expansion.

The user sees:

• the section title,
• introductory text,
• a single text field for asking a question,
• a list of the most popular questions,
• a conversation area that expands with subsequent questions and answers.

In the current version, the form also supports:

• conversation history within the session,
• clickable popular questions,
• feedback for AI answers,
• two color variants: light and dark.

The most popular product questions can be displayed below the text field.

This solution serves several purposes at once:

• speeds up the start of the conversation,
• suggests what other customers ask most often,
• allows the use of ready-made FAQ answers without the cost of a query to the AI model,
• improves UX and reduces the number of empty interactions.

Question popularity is no longer based only on manual order. The module collects data about clicks, asked questions, and feedback, and then ranks the FAQ based on that data.

The most important design assumption was that AI should not answer out of product context.

The answer can be built based on several sources:

• basic product data,
• short description,
• full description,
• selected product attributes,
• published FAQ,
• conversation history.

In addition, the module lets you limit which attributes are sent to the model, helping you avoid:

• prompt overload,
• sending unnecessary data,
• excessive token costs,
• accidentally passing content that is not useful to the customer.

One of the key expansion elements is integration with OpenAI Responses API.

In simpler scenarios, the module can work in local product and FAQ context mode. In more advanced implementations, it supports:

• file_search,
• vector_store_ids,
• filtering by sku,
• filtering by product_sku,
• filtering by store_code,
• filtering by content_type,
• limiting the number of retrieval results,
• hybrid mode,
• retrieval-first mode.

This means the AI answer can be based not only on data passed directly from Magento during a given request, but also on documents previously uploaded to Vector Store.

In practice, this provides two benefits:

• lower cost, because the full data set does not have to be sent to the model every time,
• better scalability, because retrieval can handle a larger knowledge base than a simple prompt with local JSON.

The module was prepared to work with Kowal_AiProductFeed.

This integration allows you to:

• synchronize product data to OpenAI Vector Store,
• use documents of the product.core, product.faq, product.docs, and other types,
• sync a selected product before the conversation,
• limit retrieval to specific content types.

This approach is especially useful where:

• product descriptions are long,
• the FAQ is extensive,
• the store handles many technical products,
• product data is continuously developed.

The module does not stop at generating an answer.

It also saves data that helps evaluate whether the solution works:

• number of FAQ clicks,
• number of questions asked,
• helpful / not helpful ratings,
• conversation history,
• technical metadata of AI responses,
• token usage,
• request and response payload, if diagnostic logging is enabled.

This means the implementation is not a black box. The team can analyze:

• which questions appear most often,
• whether AI uses retrieval,
• whether answers are accurate,
• which records are worth preserving as FAQ,
• how cost and quality change after modifying the prompt or configuration.

One of the most important advantages of the module is the ability to turn conversations into new FAQ entries.

The process looks as follows:

1. Customers ask questions.
2. The module saves conversations.
3. The analysis mechanism identifies FAQ candidates.
4. The administrator reviews candidates in the panel.
5. After approval, the candidate is added to the standard product FAQ.

This is a very practical work model because knowledge is not lost in conversation history. With each next iteration, the store builds a better answer layer:

• for customers,
• for the FAQ,
• for the AI Assistant,
• for future retrieval.

The module was prepared so its operation can be controlled.

Configuration includes, among other things:

• guest access restrictions,
• conversation TTL,
• request limits,
• input data sanitization,
• diagnostic logging options,
• reCAPTCHA configuration,
• controlled scope of data sent to the model.

This is important because implementing AI on the product page should not mean losing control over:

• cost,
• data,
• answer quality,
• frontend load.

The module works best in projects where:

• the catalog is larger than a few simple products,
• customers often ask about compatibility, configuration, or implementation,
• the team wants to combine a classic FAQ with a modern AI layer,
• the company develops product documentation and wants to use it in retrieval,
• control over what AI knows and where it gets its answers from is important.

It is especially well suited for stores selling:

• Magento modules,
• technical products,
• B2B solutions,
• tools that require implementation or configuration,
• products where the customer expects a fast and precise answer before purchase.

Kowal_ZapytajOProdukt is no longer just a module for a simple contact form on the product page.

It is a complete product communication layer that:

• collects questions,
• publishes FAQ,
• answers through AI,
• uses Vector Store,
• analyzes conversations,
• and turns them into an increasingly better store knowledge base.

As a result, the product page becomes a place for real conversation with the customer, not just a static page with a description and price.

In Stores → Configuration → Ask About Product, you can start with the form and FAQ plus an additional email address. You activate AI features separately: set the provider, API key, model, context scope, and Vector Store options. Integration with Kowal_AiProductFeed is optional.

AI requires API access and separate billing. Answer quality and cost depend on the context, model, and configuration. Questions that require individual confirmation can be sent to the store team through the classic form.

The package includes the optional Kowal_ZapytajOProduktHyva for the form, FAQ, and AI assistant. The adapter is disabled by default. For Hyvä, activate it additionally and check component placement in the theme you use. The Luma store uses the base module.

Package kowal/module-zapytajoprodukt, module Kowal_ZapytajOProdukt. After configuring access to the Kowal repository, install the package, enable the module, update Magento, and clear the cache. In production, include compilation and static content deployment according to the store process.

1. Configure communication
Enable the form, FAQ, and optionally the AI assistant.

2. The customer asks a question
They use ready-made questions or enter their own.

3. Expand your knowledge base
Review conversations and approve FAQ candidates.

The customer asks about product compatibility. Support answers through the form, and the repeated question can be published in the FAQ.

The optional AI assistant uses product data, FAQ, and the configured Vector Store. The administrator reviews conversation quality and suggestions for new FAQ entries.