Meet ContextCheck: Our Open-Source Framework for LLM & RAG Testing! Check it out on Github!


Client: NDA

Passenger Experience Assistance Bot

Case study details


Aiming to upgrade air transport communications and information technology, the client, a global leader in the field, embarked on an ambitious project aimed at simplifying the airport experience for passengers.

With a focus on leveraging Generative AI to boost customer service, the company partnered with Addepto, drawing on their successful collaboration in a prior Digital Twin project. This partnership aimed to bring the innovative concept of assistance bot to life, enhancing the efficiency and satisfaction of both passengers and airport personnel.



Approach


The initial application centered on supporting airport staff, including border officers, through the integration of an AI system featuring facial recognition technology, while the subsequent use case was tailored towards assisting passengers by delivering prompt and precise information regarding airport procedures and locations.



Goal


Improve the airport experience for passengers and airport staff.



Outcome


Addepto’s team crafted a cloud-based solution using GPT-4, LLamaIndex, and advanced Face Recognition algorithms. The ability to deliver human-like answers by reaching out for RAG approach in tailoring LLMs.


Our team expert opinion







Approach

Two-sided approach of AI implementation: for airport staff and passengers


During project development, our team worked on:


  • Implementing an AI solution for airports equipped with facial recognition technology. This tool would facilitate identity checks by comparing video footage with database records - the staff would be alerted in the case of any discrepancies.
  • Developing a LLM-powered airport bot. This bot, grounded in a comprehensive airport knowledge base, was designed to offer clear answers to common questions, such as terminal locations and flight delays, without requiring manual input from passengers.

Goal

AI solution for airport that improves staff and passengers experience


The envisioned LLM-powered airport bot would not only provide information but also guide passengers through the airport with the help of an integrated map, recognizing individuals and tailoring responses based on their boarding pass details. This seamless interaction was expected to make the bot an information point within the airport.




Addepto's team crafted a cloud-based solution using GPT-4, LLamaIndex, and advanced Face Recognition algorithms. The ability to deliver human-like answers by reaching out for RAG approach in tailoring LLMs.


Despite initial aspirations for a robot with a human-like face capable of expressing emotions, budget constraints led to the adoption of a simpler design featuring a virtual face displayed on a monitor equipped with a camera and microphone.


Outcome

LLM-based Airport Assistance bot - Outcome



Before


The project was aimed to achieve the ultimate goal: to improve the airport experience for passengers and airport staff. The vision was straightforward – by speeding up access to information, passengers would enjoy a more comfortable and less stressful journey, and employees would reduce the amount of manual work.



After


The implementation of the project, although it is still a PoC, can be a sign of a significant leap forward in enhancing airport efficiency and passenger satisfaction. By automating the provision of crucial information and streamlining identity checks, the project not only reduces the workload on airport staff but also significantly improves the passenger experience. The intuitive, AI-powered interaction also:

  • reduces stress and wait times, making navigation through the airport a smooth and pleasant journey
  • enhances overall safety and predictability of airport operations
  • sets a new standard in the air transport industry

We are recognized as one of the best AI, BI, and Big Data consultants


We helped multiple companies achieve their goals, but - instead of making hollow marketing claims here - we encourage you to check our Clutch scoring.

Let's discuss
a solution
for you



Edwin Lisowski

will help you estimate
your project.










Required fields

For more information about how we process your personal data see our Privacy Policy





Message sent successfully!