Persentra AI needed to turn its personalization technology into a retailer-facing control dashboard. The project scope covered frontend development for the Systema Control Centre, including merchandising rule management, recommendation controls, analytics views, and product discovery settings.
The client needed an AI personalization platform interface that retail teams could use without engineering support for routine merchandising and recommendation changes. The dashboard had to make complex AI outputs understandable through clear controls, performance metrics, and product discovery workflows.
Computools delivered the frontend for the Systema Control Centre, a web dashboard for managing eCommerce personalization software across product recommendations, real-time analytics, merchandising logic, and customer discovery scenarios. The solution gave retail teams direct control over personalization workflows and helped merchants improve AOV (Average Order Value), conversion visibility, and merchandising response speed.
Persentra AI is an Australia-based technology company that provides privacy-first personalization tools for online retailers operating in global eCommerce markets.
The company develops privacy-first artificial intelligence for retail eCommerce. Its technology helps online merchants personalize product discovery, search, content placement, and recommendations using anonymous shopper interaction signals.
The company’s AI product recommendation engine supports personalized retail experiences by adapting product visibility, discovery paths, and recommendation blocks to current shopper behavior. This gives merchants a way to improve relevance while reducing dependence on invasive personal data collection.
As a retail AI platform, Persentra AI serves online merchants who need greater control over personalization rules, merchandising logic, recommendation performance, and daily eCommerce decision-making.
Persentra AI needed a self-serve control panel that could make complex AI personalization tools usable for retail managers, merchandisers, and eCommerce teams.
The client needed eCommerce AI solutions presented through a fast, usable dashboard. Computools applied retail software development services experience to build a frontend interface aligned with retail merchandising workflows and eCommerce performance tracking.
Computools built the frontend of the Systema Control Centre using React and TypeScript. The dashboard translated Persentra AI’s personalization logic into clear controls for merchandising rules, recommendation behavior, analytics views, and product discovery settings.
The dashboard worked as an AI merchandising platform, allowing retailers to configure, adjust, and maintain merchandising rules alongside the AI engine. This helped teams guide product visibility across categories, campaigns, and recommendation zones.
Computools developed controls for personalized product recommendations, including recommendation carousels, smart search settings, and targeted product feeds. Retailers could manage how AI-driven recommendations appeared across different customer discovery flows.
The frontend displayed current performance signals, shopper behavior patterns, and recommendation outcomes through responsive dashboard views. This helped retail teams evaluate merchandising changes and recommendation logic without working directly with backend systems.
The Systema Control Centre also supported AI-powered product discovery through configurable interfaces for smart search, dynamic content, product recommendation blocks, and merchandising rule management.
The delivered Control Centre gave Persentra AI a retailer-facing dashboard for managing AI personalization across daily eCommerce operations:
The dashboard helped retail teams control real-time customer personalization without waiting on technical support for every rule or recommendation adjustment. Merchandisers could update discovery settings, review AOV and conversion impact, and act faster during campaigns or catalog changes.
The eCommerce analytics dashboard also created cleaner visibility into recommendation performance, revenue contribution, and shopper engagement. Structured recommendation, merchandising, and performance data prepared the platform for future data engineering initiatives.
Persentra AI selected Computools because the project required frontend engineers who could connect React and TypeScript development with retail dashboard logic, analytics visualization, and AI personalization workflows.
Computools focused on the workflows retail teams used daily: merchandising control, recommendation management, real-time analytics, and performance visibility. This helped Persentra AI give merchants a dashboard for managing personalization logic without technical support for routine changes.
The team collaborated with Persentra AI’s product and engineering stakeholders to deliver a responsive dashboard architecture prepared for high-frequency data updates, modular feature growth, and continued product development.
The design focused on merchandising control, product discovery management, analytics visibility, and clear AI recommendation settings for eCommerce retail teams.
Defining retail merchandising needs, personalization workflows, analytics review, and product recommendation management.
Structuring the dashboard around merchandising control, recommendation management, product discovery configuration, analytics visibility, and retailer account settings.
Designing low-fidelity layouts for the control dashboard, merchandising rule editor, recommendation controls, product discovery settings, analytics views, and retailer account workspace.
The interface gives retail teams a clear workspace for managing AI merchandising rules, recommendation controls, product discovery settings, analytics views, and revenue-impact signals.
React
React supports the dashboard frontend, including merchandising rule management, recommendation controls, analytics views, and product discovery configuration.
TypeScript
TypeScript provides typed frontend logic for reusable components, dashboard states, data-driven views, and maintainable feature expansion.
Component-based frontend architecture
Reusable components support merchandising controls, recommendation widgets, analytics panels, rule editors, and retailer account views.
Data visualization layer
Dynamic visualization components display AOV, conversion lift, revenue contribution, recommendation performance, and product discovery metrics.
API integration layer
Frontend integration with Persentra AI’s backend AI engine supports dashboard updates, merchandising rule changes, recommendation controls, and analytics data exchange.
Dashboard performance optimization
Frontend optimization supports high-frequency data updates, responsive interface behavior, and stable rendering of complex dashboard states.
An Agile approach with Scrum supported iterative frontend delivery. Work was organized into short sprints covering dashboard components, merchandising workflows, recommendation controls, analytics views, API integration, and interface performance.
Regular reviews with Persentra AI product and engineering stakeholders helped validate dashboard behavior, component logic, data visualization, and retailer-facing workflows before release.
Retail teams needed to control AI personalization without having to ask engineers to adjust every merchandising rule or recommendation setting. Computools helped us turn complex AI outputs into a dashboard merchandisers can use every day to manage discovery, monitor performance, and act faster.
Computools | 341 Raven Cir, Camden Wyoming, Delaware 19934, US
