Track Record

Case
Studies.

Over 25 years building mission-critical software for companies that demand technical excellence.

BOSCH - Shift Control
Custom Software

BOSCH - Shift Control

End-to-end production and shift management 24/7

24/7
Plant visibility
-40%
Operational incidents
100%
Operator control

The Challenge

Managing a high-output industrial plant (24/7) focused on braking system manufacturing presented a colossal logistical challenge. Coordinating rotating shifts, managing absenteeism and ensuring each operator was at the right machine was an opaque process. The lack of a unified digital tool caused planning inefficiencies, loss of real-time visibility and difficulty extracting performance metrics by operator and shift, limiting data-driven decision-making.

Our Solution

We designed and developed from scratch an industrial-grade custom web platform. This integral system acts as the plant's brain: it orchestrates morning, afternoon and night shifts, manages weekly rotations and controls leave. Through an intelligent assignment algorithm, it automatically pairs each operator with their optimal workstation. Additionally, the architecture enables real-time monitoring and telemetry, analysing productivity at a granular level and exporting interactive dashboards for management.

Technology Stack

Angular Django PostgreSQL AWS

Results

Total transformation of the plant towards an Industry 4.0 environment. 100% real-time operational visibility was achieved, radically optimising human resource management and reducing incidents caused by absences or planning errors by up to 40%. Overall productivity increased thanks to algorithmic analysis, turning the project into a reference standard exportable to other international plants within the group.

View Full Case
Regulatory Platform
SaaS Engineering

Regulatory Platform

Automated regulatory validation powered by AI

-98%
Time-to-market
AI
Expert engine
100%
PIF compliance

The Challenge

Launching a cosmetic product requires navigating an international regulatory maze. The R&D team had to manually verify ingredients, restrictions, expiry periods (PAO) and generate the Product Information File (PIF) for health authorities. This analogue process depended on external consultants, created severe bottlenecks, and a simple regulatory change could force costly market withdrawals and emergency reformulations.

Our Solution

Engineering of an AI-powered SaaS platform that digitises the entire regulatory compliance process. The expert engine autonomously analyses the complete chemical formulation, cross-referencing data against global regulatory databases. It detects current restrictions and future alerts, predicts stability interactions, recommends the optimal PAO and auto-generates audit-ready PIF documentation. All within a secured, centralised cloud ecosystem.

Technology Stack

Vue.js Python AI Engine Docker

Results

A disruptive impact on the product pipeline: 98% reduction in time-to-market for regulatory validation. The SaaS completely eliminated human errors, mitigated legal risks by anticipating future regulatory changes and generated massive cost savings by internalising processes that previously required expensive external consulting firms.

View Full Case
IM3 Engineering
Cognitive AI

IM3 Engineering

Automatic report generation from technical blueprints

10x
Processing speed
PDF
Computer Vision extraction
0
Transcription errors

The Challenge

For each new infrastructure or electrical substation, IM3 engineering needed to generate dozens of technical and descriptive reports for public administration. This critical work required highly qualified engineers to spend countless hours manually reviewing CAD blueprints and PDFs to extract technical data and fill repetitive templates — a tedious process that caused fatigue, transcription errors and severe bottlenecks in billing and project progress.

Our Solution

We deployed a bespoke Cognitive Artificial Intelligence and Computer Vision solution. The system is capable of 'reading', interpreting and semantically mapping information directly from technical blueprints and PDF diagrams. Once the information is vectorised, a language model (LLM) orchestrates the drafting of reports, adapting the format, legal jargon and specific bureaucratic requirements of each municipality or region in a fully autonomous manner.

Technology Stack

Computer Vision LLMs Python React

Results

End-to-end automation of technical bureaucracy. Administrative processing speed was multiplied by 10, freeing thousands of hours of high-value engineering. Human transcription errors were reduced to zero, and the firm increased its capacity to absorb new simultaneous projects without linearly scaling its technical workforce.

View Full Case
AI for Medical Consultation
HealthTech AI

AI for Medical Consultation

Real-time automatic clinical documentation assistant

100%
Patient focus
0h
Administrative overhead
Auto
Clinical structuring

The Challenge

The current healthcare system forces doctors to split their limited time between patient care and drafting complex clinical records. This extreme administrative burden means that during a consultation, the professional spends more time looking at a screen and typing than evaluating the patient, deteriorating diagnosis quality, eroding the human relationship and causing critical levels of burnout syndrome among medical staff.

Our Solution

Implementation of an Intelligent Clinical Assistant based on advanced language models (LLMs) and medical-precision Speech-to-Text. The AI agent passively and securely listens to the natural conversation between doctor and patient during the consultation. In real time, it analyses context, identifies symptoms and auto-generates the structured clinical report (anamnesis, examination, diagnosis and treatment) directly into the hospital software. The doctor simply reads and approves with one click.

Technology Stack

Speech-to-Text NLP Generative AI Node.js

Results

Recovery of the human factor in medicine. By eliminating the typing burden (0 hours of post-consultation administrative work), the doctor recovers 100% eye contact and attention towards the patient. Dramatic improvement in diagnosis quality, perfect standardisation of clinical records and an immediate reduction in professional stress, accelerating patient throughput across outpatient clinics.

View Full Case
Conveyor Optimizer
Industrial AI

Conveyor Optimizer

Optimal assignment and route planning for conveyor belt networks

ILP
Integer linear optimisation
A*
Pathfinding search
100%
Loading automation

The Challenge

In an industrial plant, blocks of variable dimensions must be transported through a conveyor belt network to laser-guided loading robots (LGV) located at the network's endpoints. Each robot has a maximum capacity and strict dimensional limits. The network forms a complex directed graph and the problem splits into two critical sub-problems: deciding which blocks to load onto which robots to maximise total loaded area whilst minimising robots used and distance travelled, and finding the optimal sequence of physical movements to transport blocks to the target configuration.

Our Solution

The solution is structured in three phases: first, plant modelling as a directed graph (NetworkX) with pre-computed constraint matrices (Floyd-Warshall distances, dimensional constraints, capacities and compaction lines). Second, optimal assignment formulated as Integer Linear Programming (ILP) solved with PuLP/CBC, with a multi-criteria objective function that maximises loaded area and penalises robots used and distance travelled, subject to capacity, dimension, unique assignment, fixed block, loading direction and full loading mode constraints. Third, route planning via A* search over the state space (binary block×node matrices), with an admissible heuristic based on average distance to target and reachable state generation through matrix multiplication with sequential movement, one-time load and full loading mode filters.

Technology Stack

Python NetworkX PuLP (ILP) A* Search

Results

Complete automation of assignment and movement planning across the conveyor network. The optimiser maximises each robot's payload, minimises the number of active robots and computes the optimal movement sequence, eliminating manual planning and assignment errors. The admissible A* heuristic guarantees solution optimality, whilst the non-admissible variant enables faster viable solutions in high-complexity scenarios.

View Full Case
PlannSat
SaaS Platform

PlannSat

SaaS software for digitalising maintenance processes

+20%
Profitability increase
GPS
Real-time tracking
SaaS
Multi-sector

The Challenge

Installation, maintenance and repair companies across sectors such as HVAC, solar energy, lifts and cleaning services were managing their interventions manually using spreadsheets and paper. This led to loss of control over worker productivity, errors in intervention planning, difficulty with real-time monitoring and lack of visibility into the actual profitability of each client and project.

Our Solution

End-to-end development of PlannSat, a complete SaaS platform with a web management panel and mobile application. The system includes workflow management with an intelligent intervention calendar, task assignment and prioritisation per worker, real-time GPS tracking of workers on route, comprehensive client management with installation maps and intervention history, payment control and per-client profitability analysis, and exportable report generation. Fully accessible to both managers and field workers.

Technology Stack

Angular Node.js PostgreSQL Google Maps API Firebase Webflow

Results

Complete digitalisation of maintenance processes for companies across multiple sectors. Business optimisation, control and profitability increased by 12–20%. Elimination of paper and spreadsheets, real-time visibility of each worker's productivity, efficient intervention planning and total expense and payment control from a single platform.

View Full Case
DAEDO
Sports Technology

DAEDO

Electronic scoring software for Olympic and World Championship Taekwondo

WT
World Taekwondo certified
Olympics
Used at Olympic Games
GEN3
3rd generation PSS

The Challenge

Olympic and world-level taekwondo bouts required an electronic scoring system (PSS — Protector & Scoring System) guaranteeing maximum precision, reliability and speed in impact detection. The system had to process real-time data from sensors embedded in body protectors (chest guards), helmets and electronic shin guards, transmitting wirelessly to digital scoreboards and refereeing panels — all under competition conditions with thousands of spectators and international television broadcast.

Our Solution

End-to-end software development for the DAEDO GEN3 PSS system, officially certified by World Taekwondo (WT). The platform includes real-time impact signal processing with inertial and piezoelectric sensors, high-reliability wireless transmission between protectors and the central system, digital scoreboard with scoring management, penalties, rounds and timing, referee control panel with instant point validation, integrated video replay system, and full tournament management with elimination brackets, weight categories and rankings.

Technology Stack

C++ Embedded Systems Bluetooth LE Real-time OS Qt Node.js

Results

System certified by World Taekwondo and used at the Olympic Games, World Championships and international Grand Prix events. Millimetre-precision impact detection, eliminating the subjectivity of manual refereeing. Zero-perceptible-latency wireless transmission, digital scoreboards integrated with television broadcast and automated tournament management for thousands of competitors.

View Full Case
TripTango
Fleet Management

TripTango

Fleet management platform with GPS geolocation and route optimisation

GPS
Real-time tracking
-30%
Operating cost reduction
24/7
Continuous monitoring

The Challenge

Transport and logistics companies lacked real-time visibility into the location and status of their vehicle fleets. Manual route planning led to inefficiencies, excessive fuel consumption, downtime and a lack of control over driver activity. Furthermore, the absence of historical data prevented strategic decision-making to optimise operations.

Our Solution

End-to-end development of TripTango, a fleet management platform with real-time GPS geolocation. The system includes live vehicle tracking on an interactive map, algorithmic route optimisation with ETA calculation, geofencing management with automatic zone entry and exit alerts, driver control panel with performance and driving behaviour metrics, fuel consumption analysis, scheduled preventive maintenance with alerts, operational and compliance report generation, and integration with OBD-II devices and onboard IoT sensors.

Technology Stack

Angular Node.js PostgreSQL Google Maps API WebSockets IoT / OBD-II

Results

Total fleet visibility in real time, operating cost reduction of up to 30%, automatic route optimisation with significant fuel and time savings. Complete control of driver activity, proactive maintenance alerts preventing costly breakdowns and automated reporting for regulatory compliance.

View Full Case

Tu caso
de éxito.

Over 25 years building mission-critical software for companies that demand technical excellence.

Inicia tu proyecto

Contact

Let's talk about
your Project.

Over 25 years transforming businesses with custom software. Tell us your challenge and we'll design the solution.

Barcelona — HQ

Av/ Diagonal 449, 4ª

08036 Barcelona, Spain

+34 93 363 50 93

Bilbao

C/San Vicente nº 8, 6ª

48001 Bilbao, Spain

+34 94 424 26 90

By submitting this form, you accept our privacy policy. We will respond within 24 business hours.