Applied research to advance agentic customer experiences
Benchmarks, controlled experiments, and engineering insights for building reliable AI agents for customer experience.
Research index
09 articles-
Voiceflow vs Claude: where CX decisions go wrong
In 320 controlled CX trials, all four models made refund errors. Compare Voiceflow and Claude on policy decisions and exact amounts separately.
-
Enhancing user experience: from NLU intents to RAG with embeddings
We're excited to introduce intent recognition powered by Retrieval-Augmented Generation (RAG): enhancing user experience from NLU intents to RAG with embeddings.
-
5 tips to optimize your LLM intent classification prompts
We tested over 500 prompt variations across two datasets to see how to improve LLM intent classification.
-
Benchmarking hybrid LLM classification systems
Benchmarking hybrid LLM classification systems: a deep dive into hallucinations, accuracy, costs, latencies, usability and context window analysis.
-
How much do ChatGPT versions affect real-world performance?
Do versions change your performance by 1% or 10%? Let’s dive into a production-impacting LLM task and how model versions impacts agent performance.
-
Improving performance of Hybrid Intent + RAG conversational AI agents
A case study on opinionated decisions when launching products, balancing speed to build, accuracy and speed to iterate.
-
Large Action Models change the way we build chatbots, again
How Large Action Models will change the way we build chatbots, again: applied research on Large Action Models and the way chatbots get built.
-
Creating the Voiceflow NLU
We started working on the Voiceflow NLU in February 2022, and this is a small slice of our story: the applied research behind creating the Voiceflow NLU.
-
NLU design: How to train and use a natural language understanding model
Learn the basics of NLU models and how teams are training/using them for conversational AI experiences.