February 2024 Summaries
2 posts from Voiceflow
Filter
Month:
Year:
Post Summaries
Back to Blog
Trilogy's Atlas Core is a core AI agent in Voiceflow that contains foundational building blocks for several complex agents, enabling the company to scale AI agents quickly and add features to specific products while maintaining a complex core that is continually improved. The team also built a standalone ticket triaging and answering agent, called Atlas Ticket, which automatically analyzes user queries and answers them drawing from a database of company-specific information. Trilogy refined their knowledge base to continually improve responses and built trust with hesitant customers by including context in the agent's answers. The effect on Trilogy's support systems was immediate, with a 35% AI resolution rate on support tickets within the first week of deploying Voiceflow. The company has seen significant strides in four major areas, including AI resolving over half of all support tickets and reducing tedious research by using a knowledge base.
Feb 29, 2024
1,278 words in the original blog post.
The journey from Clippy to artificial intelligence has been gradual, with digital assistants evolving from hardcoded agents using the Understand, Decide, Respond model to more advanced AI models like Natural Language Understanding and Large Language Models. These models enable agents to predict their responses and actions based on a confidence-ranked range of possibilities and given inputs, producing more fluid and natural conversational experiences. However, the risk of "hallucinations" remains, particularly in tasks that require high accuracy, such as issuing refunds. Recent advancements in Large Action Models (LAMs) have the potential to make agents fully probabilistic end-to-end, but their effectiveness and reliability are still uncertain. As LAMs become widespread, they may change how agents are built, with decision logic being abstracted and simplified, and conversation designers focusing on designing permission systems for where and when a LAM can call a particular function. The adoption of LAMs is expected to bring about new opportunities and challenges for the industry, including the need for more advanced training and management tools.
Feb 14, 2024
933 words in the original blog post.