Unlike traditional AI, which analyses data and makes predictions, GenAI uses advanced algorithms to generate content in various formats, such as text, images, and music, based on patterns learned during its training process.
As part of the Autonomous Network Journey (ANJ) programme, Telefónica is evaluating how to apply GenAI to transform its operational processes towards a more autonomous environment. One of the main focuses of this analysis is the management of the large volumes of technical information that its technicians deal with on a daily basis.
Currently, when a technician needs to consult a specific topic, resolve a specific issue, look up component characteristics or know the sequence of actions to solve an incident, he usually spends a considerable amount of time searching through manufacturers’ manuals. These documents, often lengthy, complex, sometimes unclear and written in different languages, further complicate the task. In this scenario, who wouldn’t want a ‘partner’ who could provide immediate and accurate answers?
To improve this situation, Telefónica España, through its Optical Network Technology and Configuration area, decided to launch a proof of concept (PoC) of a technical documentation ChatBot. The objective of this project is to evaluate the applicability and benefits of having a tool powered by artificial intelligence to assist technicians in their daily work.
The ChatBot developed by Telefónica España offers an intuitive interface that allows technicians to ask questions in a natural way and in Spanish, and to receive coherent, accurate answers in Spanish about devices and equipment in the transport network, thus improving their operational efficiency.
The ChatBot uses GenAI to consult the technical manuals and internal configuration documents that have been previously provided and generates the answer that the technician needs. This response is in the technician’s own language and has references to the manuals where the relevant information has been found.
The solution is based on the RAG (Retrieval-Augmented Generation) methodology, an advanced technique that combines the retrieval of relevant information with the ability to generate answers by a language model (LLM). This approach is especially useful in cases where accuracy is crucial, such as querying complex technical manuals. The integration of RAG into the ChatBot significantly improves its conversational capabilities, enabling more complete, contextual and accurate responses, which optimises the technicians’ day-to-day experience.
After a period of training and management to adapt it to the type of questions usually asked and demanded by Telefónica España’s technicians, the technical documentation ChatBot has been a success, bringing the following benefits to the process:
- Automation of consultation tasks: freeing up time for technicians to focus on more complex activities.
- Improved efficiency in the consultation of technical documentation. Consume less time searching through manuals.
- Fast response: Provide instant responses, improving the user experience and reducing waiting times.
- Scalability: Can serve multiple users simultaneously from different areas.
- Consistency: Provides uniform and accurate responses, ensuring consistency.
- 24/7 availability: They can respond to questions and provide assistance at any time.
Benefits and KPIs impacted
The future of this documentation ChatBot is promising, as it can enable any type of documents such as engineering criteria, alarms or control plane configuration, among others. All this centralised to be accessible from the ChatBot in a single place and environment and integrated with the main operation systems.
The expected benefits are in 5 areas:
- Increased productivity, as technicians focus on higher value tasks.
- Increased multi-purpose resources.
- Accelerates the learning curve. It helps new resources in the organisation by facilitating their learning.
- Quality, clarity and transparency in the answers.
- Natural communication with the environment and even in the same language as the technician.
As for the KPIs impacted, the challenge is great and work is focused on the following:
- Information search time.
- Time to solve problems.
- Time to adapt a resource to the network/technology plan.
- Percentage of correct answers and clarity.
This type of initiative, supported by GenAI’s advanced techniques, enables the integration of AI into operational processes and promotes the level 4 autonomy of an Operator.
What’s Next?
This type of initiative, supported by GenAI’s advanced techniques, enables the integration of AI into operational processes and promotes the level 4 autonomy. Furthermore, it also being implemented in other areas of the company to increase sales productivity, improve NPS, and reduce churn.
A prominent example of the implementation of RAG technology is the development of Aura Copilots, intelligent assistants that Telefónica is working on. These assistants allow employees to query, customize, and manage information on specific areas using data sets and Kernel APIs, as well as procedural documentation. This solution facilitates real-time access to information, enhances service management and operations, and delivers smarter experiences, supporting the strategy of digitalization and centralization in leveraging customer data.
AI technology is not only optimizing internal resources and processes but also strengthening Telefónica’s commitment to innovation, preparing the company to face the challenges of an increasingly digital and autonomous environment.
