PrestaShop AI Reporting
PrestaShop AI Reporting enables store administrators to analyze their store data using natural language. Instead of manually creating complex reports, you can simply ask questions about your store and get the results in an easy-to-understand table or chart.
The module allows you to generate reports from multiple store entities, including Orders, Refunds, Products, Customers, Product Inventory, Categories, Abandoned Carts, Product Reviews, and Wishlists. You can connect the module with a Webkul preconfigured AI endpoint or use your own API key from supported AI providers.
- Description
- Reviews
- FAQ
- Customers ()
- Specifications
- Cloud Hosting
- Changelog
Most PrestaShop reporting forces a choice: a static Stats block that answers only the questions it was built for, or a custom module that has to be rewritten every time the shop owner thinks of a new question. In between sits the alternative most stores actually use — opening phpMyAdmin and writing SQL by hand. That is slow, it is error-prone, and it is completely unavailable to anyone who does not already know the database schema.
AI Reporting removes that middle ground. You type a question the way you would ask a colleague — "top 5 products by revenue this month", "how many orders are waiting to be shipped", "which customers have not ordered in 90 days" — and the module turns it into a query, runs it safely, and returns a table or a chart you can read, adjust, export or save. It is built for shop owners, managers and marketing staff who need an answer today, not for the developer who would otherwise have to write it.
This PrestaShop edition reads your data through a hybrid layer. Orders, order line items, Products and Customers are served from dedicated denormalised flat tables that you rebuild on demand, so the heavy questions stay fast. The remaining entities — Refunds, Product Inventory, Category, Abandoned Cart, Product Reviews and Wishlist — are queried live through a curated, read-only whitelist. Product Reviews and Wishlist appear only when the productcomments and blockwishlist modules are installed, and disappear again automatically when they are not.
Additionally, you can grow your reporting surface by integrating AI Reporting with your other Webkul modules.
Highlighted Features
Natural-language reporting
Type a question in ordinary language and the configured AI provider converts it into SQL, which the module then guards and runs against your shop data. The answer comes back as a result grid you can read, chart, export or save.
Nine reporting entities
Orders, Refunds, Products, Customers, Product Inventory, Category, Abandoned Cart, Product Reviews and Wishlist. You decide which of them the AI is allowed to query, and at least one must stay enabled.
Five result views
Every result can be shown as a table, a line chart, a pie chart, a bar chart or an area chart. A dedicated panel lets you set the chart label and choose which column feeds the X-axis and which feeds the Y-axis, without re-running the query.
CSV and PNG export
Download the table view as a CSV file whose header row uses the same readable column headings the page shows, and download any chart view as a PNG image generated in the browser.
AI Reporting Magic Search
The Magic Search page is where a question becomes a result. Type it, and the module builds a prompt containing your schema and worked examples, sends it to your configured AI provider, guards the returned SQL and executes it.
- Ask questions in plain language with a single search box and a set of example prompts
- Switch the same result between table, line, pie, bar and area views without re-running the query
- Set the chart label, X-axis column and Y-axis column from a dedicated panel
- Read the exact SQL behind any result in a dedicated SQL view, with a Copy SQL control
- Download the table as CSV or the chart as a PNG image
- Save any result as a named report with its chart type and axes

AI Reporting Flat Tables and Rebuild
Orders, order line items, Products and Customers are copied into dedicated flat tables so the questions that matter most run fast. The rebuild is yours to trigger, per entity, and reports progress live while it works.
- Rebuild Orders, Products or Customers individually from the configuration screen
- Watch per-entity live progress, row counts and Pending, Running, Done or Failed status
- Optional columns for orders, order items, products and customers are chosen from a checkbox picker, and the tables are rebuilt to match
- Schedule unattended rebuilds through a cron URL protected by a generated token

AI Reporting Provider Setup
Two ways to connect an AI service are supported, and both are configured from the same General screen. The active type is preconfigured as a self-hosted or hosted reporting endpoint with a token key, while the LLM Provider type talks directly to one of six supported vendors.
- Preconfigured: set a reporting endpoint URL and a token key, then validate the endpoint and push your schema to it
- LLM Provider: pick OpenAI, Gemini, Anthropic, OpenRouter, Cerebras or DeepSeek
- Choose a model from a list fetched live from the provider, with a built-in fallback list if the fetch fails
- Run a Validate Provider check that sends a real connectivity test and reports Valid or Invalid
- The API key is stored encrypted and is never written as a plain configuration row; clearing the field keeps the saved key

AI Reporting Saved Reports Dashboard
Saved reports live in their own Back Office section with two interchangeable modes. The list gives you search, filtering and bulk delete; the dashboard gives you a wall of live cards.
- List mode with sortable and filterable columns for label, question, chart type and creation date
- View a single saved report to see its stored definition and its freshly executed result
- Dashboard mode draws two report cards per row and re-runs every saved report on page load
- Reorder reports by dragging and delete them individually or in bulk
- Every saved report is scoped to the shop it was created under

Features of AI Reporting
- Turn a plain-English question into SQL and return the answer as a table or chart.
- Report on nine entities: Orders, Refunds, Products, Customers, Product Inventory, Category, Abandoned Cart, Product Reviews and Wishlist.
- Serve Orders, Products and Customers from rebuildable flat tables for fast queries.
- Connect to a Webkul preconfigured endpoint or your own OpenAI, Gemini, Anthropic, OpenRouter, Cerebras or DeepSeek key.
- Guard every generated query with a single-statement check, a keyword blacklist and a table/column whitelist.
- Switch between table, line, pie, bar and area chart views and inspect the generated SQL.
- Save reports to a dashboard that reorders, re-runs and redraws them on load.
- Export table results as CSV and chart views as PNG.
- Rebuild flat tables on demand from the configuration screen or on a token-guarded cron schedule.
Support
For any query or issue, please create a support ticket here: https://webkul.uvdesk.com/en/customer/create-ticket/ You may also check our quality PrestaShop Module: https://store.webkul.com/PrestaShop-Extensions.html
Specifications
Frequently Asked Questions
Specification
Detailed technical features and requirements to help you understand the module’s capabilities and ensure smooth integration with your system.
Cloud Hosting
Detailed technical features and requirements to help you understand the module’s capabilities and ensure smooth integration with your system.
Move to Cloud Today
We’re partnered with top-tier, trusted providers!
Default Configuration Details of Server
RAM 1 Core
Processor 30 GB
Hard Disk
Database
Want to know more how exactly we are going to power up your eCommerce Website with Cloud to fasten up your store
* Server Configuration may vary as per application requirements.