New Beef Feedlot is part of a broader ecosystem focused on precision livestock farming, integrating data, artificial intelligence, and operational management.

The platform enables:

• Monitoring animal performance

• Optimizing feeding strategies

• Predicting weight gain and slaughter timing

• Managing financial and operational indicators

The project focuses on the modernization of a legacy system with high adoption in the livestock industry, especially in Brazil, now expanding globally.

Despite its strong market presence, the previous system presented:

• Outdated technology

• Poor usability

• Fragmented workflows

• Limited scalability

Problem Complexity

This project operates at a highly complex intersection:

• Scale: management of some of the largest cattle operations in the world

• Biological variability: animal performance influenced by multiple factors

• Operational complexity: feeding, health, logistics, cost management

• Data density: multiple real-time inputs and predictive models

• User diversity: from highly technical operators to low digital literacy users

• Global expansion: need for adaptability across regions and regulations

• operational intelligence;

• cognitive load;

• decision support.

The challenge was to reduce cognitive load and transform dense operational workflows into intuitive decision-support experiences without sacrificing reliability, flexibility, or system depth.

Process

The project follows a continuous discovery and delivery model within agile methodology, combining structured research, rapid iteration, and data-driven validation.

Main stages:

• Brainwriting and diagrams

• Blueprints (system and journey mapping)

• Interview script design

• Customer interviews

• Insight generation

• JTBD definition

• Ideation with Figma Make

• Low-fidelity prototyping

• Design System creation

• High-fidelity prototyping

• Validation and metrics tracking

Discovery (Blueprint + Research)

We started with a Blueprint to understand the full ecosystem:

• End-to-end user journeys

• Operational dependencies

• Data flows

• Pain points

User Research

Conducted interviews with real customers to understand:

• Daily operational workflows

• Decision-making processes

• Data interpretation challenges

• Informal workarounds

Insights & JTBD

Research findings were translated into actionable insights, structured using Jobs To Be Done (JTBD).

This enabled alignment between product features and real needs such as:

• Monitoring herd performance

• Optimizing feed efficiency

• Reducing operational costs

• Supporting critical decisions

Guideline & Design System

A Design System was created to support:

• Consistency across the platform

• Scalability for new features

• Adaptation for international expansion

AI-assisted Decision Support

One of the core product principles was shifting the experience from passive data visualization to active operational support.

The platform integrates predictive models and operational indicators to help users:

• anticipate performance outcomes

• optimize feeding strategies

• identify operational bottlenecks

• prioritize critical actions

• reduce uncertainty in day-to-day decisions

The UX strategy focused on making AI-driven insights understandable, actionable, and seamlessly integrated into real operational workflows.

Ideation & Low-Fidelity Prototyping

Leveraged AI-assisted design workflows with Figma Make to accelerate ideation, explore interaction patterns, and rapidly prototype complex operational scenarios:

Key activities:

• Generated low-fidelity prototypes

• Tested multiple interaction models

• Simplified complex data visualization

High-Fidelity Design

High-fidelity prototypes focused on:

• Data visualization clarity

• Hierarchical organization of information

• Efficient workflows for decision-making

  
  

Validation & Development

The project runs in an agile environment, with strong collaboration between Design and Engineering.

Validation included:

• Pilot Customer Interviews

• Usability testing

• Accessibility validation

• Interface consistency testing

Design decisions were validated alongside developers to ensure feasibility and qualit

Data & Metrics (Tableau + Google Analytics)

A key differentiator is the continuous monitoring of real usage data.

Tools:

• Tableau → operational and product metrics

• Google Analytics → user behavior tracking

Focus:

• Feature usage

• User flows

• Drop-offs

• Interaction patterns

Behavioral and operational metrics continuously informed prioritization, workflow optimization, and evolution of AI-assisted product experiences.

Results & Expansion

The platform has been validated through pilot programs, with strong adoption and positive feedback.

Current stage:

• Expansion in Latin America and Mexico (pilot phase)

• Progressing to Phase 3: Europe expansion (second half of 2026)

Vision:

• To become a globally scalable platform, supporting livestock operations worldwide.

Key Takeaways

• AI products only create value when insights are actionable within real workflows

• Operational complexity should be abstracted, not exposed

• Scalable platforms require alignment between systems thinking, business strategy, and user behavior

• Predictive experiences depend as much on UX clarity as on data quality

• Enterprise products must balance flexibility, operational depth, and usability simultaneously