All Foundries

Commodity Management & Trading

Transforming trading ecosystems through data-driven insights and secure, agile platforms that empower global commerce.

Customer & Marketing Strategy

Reimagining customer engagement with personalized, connected experiences that build trust and long-term value.

Digital Engineering

Turning ideas into scalable digital solutions—accelerating transformation through design, technology, and engineering excellence.

Station Studio

Redefining mobility hubs with digital innovation to create smarter, sustainable experiences for people and businesses on the move.

Supply Chain & Industry 5.0

Building resilient, intelligent supply networks that anticipate change and deliver efficiency with purpose.

Sustainability

Driving responsible innovation to help organizations achieve net-zero goals and create a positive impact for future generations.

Physical AI

Physical AI gives machines, robots and physical operations the ability to perceive their environment, decide what matters and act in real time. Factories, plants, stores and infrastructure become systems able to sense conditions, learn from them and improve on their own, closing the gap between the physical and the digital world.

Next-Gen Infrastructure

From networks as infrastructure to connected platforms that enable critical, autonomous and intelligent operations.

Retail

From satisfaction surveys to EBITDA: closing the loop on customer pain points

A department store retailer in Mexico turned a biannual NPS programme into a closed-loop customer listening mechanism, connecting feedback to pain-point initiatives and incremental EBITDA.

From satisfaction surveys to EBITDA: closing the loop on customer pain points

Retail

Unified returns management

A retailer processing more than two million returns a year moved from channel-specific workflows toward one digital returns system. The initiative connects request creation, status tracking and routing across sales and return channels.

Unified returns management

Contact

AI-Powered Video Situational Awareness with Explainable Alerts

Critical moments in physical operations are easy to record, but harder to understand. Across industrial, public, corrections and energy and utilities environments, a vision-language-model platform turns live video into contextual, explainable alerts, helping teams move from passive monitoring to operational follow-up.

Utility technician walking through an electrical substation monitored by fixed cameras at dawn.

Contextual detection

Critical events interpreted in context

Monitoring effort

Reduced manual review reported

Rule scalability

New scenarios without retraining

Alert transparency

Trigger reasons made explainable

Operations professionals coordinate a response near pipes and treatment equipment at a water utility.

AI-powered video situational awareness

Natural-language monitoring rules and contextual video understanding bring explainable intelligence into critical physical operations.

When detection is not enough, context becomes operational

Objectives

The initiative set out to turn live video from critical environments into operational insight that teams can understand, trace and act on. It needed to interpret not only objects, but also behaviors and interactions; allow users to describe monitoring conditions in everyday language; and connect qualified alerts with inspection, safety, maintenance and remote-execution workflows.

Opportunity

The platform creates a path to apply a shared situational-awareness layer across HSE, perimeter security, fire and smoke, anomalous-behavior and critical-site monitoring. Because monitoring logic can be expressed in natural language and enriched with regional context, organizations can explore new rules and use cases without commissioning a separate algorithm for each scenario. The source also identifies robotics, drones, machine vision, positioning and immersive technologies as potential channels for field evidence.

Video was abundant. Operational understanding was not

The initiative needed to move beyond isolated detection and fit the way operations, engineering and maintenance teams review evidence, make decisions and follow through in the field.

Key Challenges

Maintenance activities, vehicles and equipment create a complex scene inside an electrical substation.

1: Signals without context
Traditional analytics could identify objects, but often struggled to distinguish the behaviors, interactions and circumstances that made an event operationally relevant.

Utility security operator manually reviews multiple live feeds from critical infrastructure sites.

2: Manual review at scale
Large volumes of video still required operator attention, consuming effort and slowing the route from observation to response.

Utility safety lead and field engineer walk between a solar farm and switching station to assess changing monitoring needs.

3: Rules that had to move
Different sites, regions and use cases required monitoring logic that could adapt without a new algorithm for every condition.

Engineering and maintenance staff organize drone inspection evidence beside a hydroelectric facility.

4: Evidence without a workflow
Captured footage needed to become traceable information that engineering, operations and maintenance teams could review and act on consistently.

Solution

A contextual intelligence layer for physical operations

The delivery connected field evidence, vision-language interpretation, user-defined rules and operational follow-up in one repeatable chain, designed to support scalable use beyond isolated demonstrations.

Vision-language scene understanding

Vision-language models interpreted scenes, objects, actions and interactions, providing the contextual layer required to assess whether defined conditions were present.

Qualified, explainable alerts

The platform generated alerts when contextual conditions were met and explained why each alert was triggered, reducing reliance on continuous manual review.

Natural-language monitoring rules

Users could define and adjust monitoring logic in plain language, with support for region-specific conditions and multiple safety and security scenarios.

From evidence to action

Field capture and digital processing were linked with review and operational follow-up, supporting repeatable missions and procedures across physical environments.

Impact

More flexible situational awareness, with reasoning teams can follow

By interpreting context rather than objects alone, the platform supports more accurate identification of critical events and reduces the effort tied to continuous manual monitoring. Natural-language rules allow the same capability to extend across use cases without retraining for each scenario, while explainable alerts give teams a clearer basis for review and follow-up. Together, these capabilities strengthen safety, risk mitigation and traceability across physical operations.

Featured
success stories

Empowering field operations through digitalized service management and improving safety conditions trough connected worker technologies

View all success stories