Your browser does not support the audio element
Image Source: ChatGPT-4oAda
Ada, an AI-native customer service automation platform, is driving a $100B transformation in customer service spending. Since its founding in 2016, Ada has grown to a valuation of $1.2B, securing $200M in funding. The platform is used by notable brands such as Verizon, YETI, Canva, and Square.
From NLP to GPT-4: A New Era of AI for Ada
Ada initially built its platform using custom Natural Language Processing (NLP) models, but there was a gap in resolving customer queries effectively. According to Mike Gozzo, Ada’s Chief Product and Technology Officer, the team became excited by the possibilities of OpenAI’s large language models (LLMs). In 2022, they made the decision to rebuild their product with a focus on reasoning capabilities offered by these advanced models.
The Limitations of Traditional NLP
Traditional NLP models were not equipped to handle complex customer queries. They often struggled to provide accurate and relevant responses, leading to frustration for both customers and agents. Ada recognized that there was a need for more sophisticated AI capabilities, which led them to explore the potential of OpenAI’s large language models.
The Benefits of GPT-4
GPT-4 offers several benefits over traditional NLP models, including:
- Improved accuracy: GPT-4 is able to provide more accurate and relevant responses to customer queries.
- Increased efficiency: GPT-4 can handle a higher volume of conversations than traditional NLP models, making it an ideal solution for large-scale customer service automation.
- Enhanced user experience: GPT-4 provides a more natural and intuitive user experience, which leads to increased customer satisfaction.
Introducing a New Customer Service Metric: Resolution Rate
Traditionally, customer service automation has been measured by the containment rate – how many queries are handled by chatbots without human intervention. However, Ada found that achieving high containment rates didn’t necessarily mean good customer experiences. The team shifted their focus to resolution rate, which measures how well conversations are resolved without human assistance.
Developing an Evaluation Framework
Ada developed an evaluation framework that rates conversations based on customer satisfaction, accuracy, and safety of replies. By integrating GPT-4 with their historical data, they were able to create a robust system for measuring the effectiveness of their AI-powered automation.
Achieving Higher Resolution Rates and Customer Satisfaction
Ada’s AI Agent, powered by OpenAI’s multi-agent configuration, processes customer queries through several iterations of reasoning & understanding, using tools, and knowledge gathering. This approach has significantly increased the resolution rate of customer queries.
- Improved resolution rates: With their new system, Ada is able to resolve 60% of customer queries without human assistance.
- Increased customer satisfaction: Customers are more satisfied with the service they receive from Ada’s AI-powered automation.
- Enhanced user experience: The natural and intuitive interface of GPT-4 provides a better user experience for customers.
Looking Ahead: Aiming for 100% Resolution Rate
Ada is confident that they will eventually reach a 100% resolution rate. With the continued development of their platform and the integration of new technologies, they are well on their way to achieving this goal.
- Transparency: Ada plans to increase transparency in their product, allowing customers to better understand how their AI-powered automation works.
- Control levers: The company aims to provide more control levers for customers, enabling them to fine-tune the performance of their AI Agents.
Conclusion
Ada’s use of GPT-4 has revolutionized the customer service industry. By providing a more accurate and efficient solution for resolving customer queries, Ada is able to improve customer satisfaction and reduce costs for businesses.
- Improved accuracy: GPT-4 provides more accurate responses to customer queries.
- Increased efficiency: GPT-4 can handle a higher volume of conversations than traditional NLP models.
- Enhanced user experience: GPT-4 provides a more natural and intuitive user experience.
