/
Juango

helping a logistics company transform their legacy

Juango is a freight and warehouse management company that spans their services across a growing number of Latin American countries. A 30+ years old company, they saw the potential of technology to help them radically transform their offering with the end goal of achieving exponential growth.

The challenge

To digitally transform its structure to reduce inefficiencies and achieve its expected growth levels, Juango realized it was time to make a change that would allow it to be one step ahead of the game.


As an additional level of complexity, the goal was to reduce their dependence on human dispatchers that organized and assigned physical resources while simultaneously maintaining its operations and levels of activity with zero downtime. 

To digitally transform its structure to reduce inefficiencies and achieve its expected growth levels, Juango realized it was time to make a change that would allow it to be one step ahead of the game.


As an additional level of complexity, the goal was to reduce their dependence on human dispatchers that organized and assigned physical resources while simultaneously maintaining its operations and levels of activity with zero downtime. 

The outcome

Juango has transformed its processes and expanded its business reach and efficiency as a result of the inclusion of Artificial Intelligence. It can now make the best possible decisions based on available information and maximize the value they deliver to their customers in the light of this knowledge.


Our solution proved relevant for Juango, delivering improvements across the board by including restraints in the planning process:

Juango has transformed its processes and expanded its business reach and efficiency as a result of the inclusion of Artificial Intelligence. It can now make the best possible decisions based on available information and maximize the value they deliver to their customers in the light of this knowledge.


Our solution proved relevant for Juango, delivering improvements across the board by including restraints in the planning process:

-43%

time spent in journey
and fleet planning

-31%

in route costs,
including gas and personel
Better time efficiencies
& less repetitive tasks
Seamlessly supports a growing number of clients.

-43%

time spent in journey
and fleet planning

-31%

in route costs,
including gas and personel

Better time efficiencies
& less repetitive tasks
Seamlessly supports a growing number of clients.

The growing pains of a thriving business

Juango grew from a family business that owned 2 trucks to a company in control of siloes and warehouses. The increment in fleet -and general market growth- size meant a technical input was needed in order to keep the business running smoothly: up to that point, Juango had little to no active digitalization practices.

The company relied on experience and dispatchers as well as other relevant logistics personnel, but daily operations often made them a bottleneck for decision making.   

Juango realized the organization of knowledge acquired through the years in a scalable way that could grow along with them was due. And that’s when Arionkoder came in.

The growing pains of a thriving business

Juango grew from a family business that owned 2 trucks to a company in control of siloes and warehouses. The increment in fleet -and general market growth- size meant a technical input was needed in order to keep the business running smoothly: up to that point, Juango had little to no active digitalization practices.

The company relied on experience and dispatchers as well as other relevant logistics personnel, but daily operations often made them a bottleneck for decision making.   

Juango realized the organization of knowledge acquired through the years in a scalable way that could grow along with them was due. And that’s when Arionkoder came in.

The way forward

The Arionkoder team analyzed the company’s processes through a series of interviews with all relevant stakeholders and discovered that the information that existed within the company needed systematization; while other valuable information was not being captured and utilized.

This volume of information required a new approach to addressing the logistical challenges and needs of the company. We suggested the implementation of Constraint Programming, an AI paradigm that solves combinatorial problems. Its main appeal is its ability to work with a number of real-world variables simultaneously, including them as restrictions that shape the proposed solutions.

Constraint Programming is also an interesting choice because of its ease of maintenance, which is something that alternative solutions such as imperative or object-oriented programming lack, ensuring the project's viability over time.

We also employed Machine Learning resources as a fundamental first step in the road to AI. Additionally, to address the information that was not yet being captured, we used IoT sensors both in the freight and in different locations that allow for key information to be delivered in real-time.

The Arionkoder team analyzed the company’s processes through a series of interviews with all relevant stakeholders and discovered that the information that existed within the company needed systematization; while other valuable information was not being captured and utilized.

This volume of information required a new approach to addressing the logistical challenges and needs of the company. We suggested the implementation of Constraint Programming, an AI paradigm that solves combinatorial problems. Its main appeal is its ability to work with a number of real-world variables simultaneously, including them as restrictions that shape the proposed solutions.

Constraint Programming is also an interesting choice because of its ease of maintenance, which is something that alternative solutions such as imperative or object-oriented programming lack, ensuring the project's viability over time.

We also employed Machine Learning resources as a fundamental first step in the road to AI. Additionally, to address the information that was not yet being captured, we used IoT sensors both in the freight and in different locations that allow for key information to be delivered in real-time.

The Arionkoder team analyzed the company’s processes through a series of interviews with all relevant stakeholders and discovered that the information that existed within the company needed systematization; while other valuable information was not being captured and utilized.

This volume of information required a new approach to addressing the logistical challenges and needs of the company. We suggested the implementation of Constraint Programming, an AI paradigm that solves combinatorial problems. Its main appeal is its ability to work with a number of real-world variables simultaneously, including them as restrictions that shape the proposed solutions.

Constraint Programming is also an interesting choice because of its ease of maintenance, which is something that alternative solutions such as imperative or object-oriented programming lack, ensuring the project's viability over time.

We also employed Machine Learning resources as a fundamental first step in the road to AI. Additionally, to address the information that was not yet being captured, we used IoT sensors both in the freight and in different locations that allow for key information to be delivered in real-time.

Project Breakdown

Initial Team:

1 ML Engineer

3 Developers

1 QA

1 UX/UI

1 PM

Initial Team:

1 ML Engineer

3 Developers

1 QA

1 UX/UI

1 PM

Ongoing Team:

2 Devs + Part time QA + PM Support

Ongoing Team:

2 Devs + Part time QA + PM Support

Tech Stack: Angular, Google OR-Tools, Python, Pentaho.

Tech Stack: Angular, Google OR-Tools, Python, Pentaho.

Logo
Logo
Logo
Logo
Logo
Logo
Logo
Logo
Logo
Logo
"I don’t think they could’ve made it better."

Nicolas Rodriguez

CIO @ Juango Logistica

"I don’t think they could’ve made it better."

Nicolas Rodriguez

CIO @ Juango Logistica