BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//global2024.pydata.org//cfp//AJT8R7
BEGIN:VEVENT
UID:pretalx-cfp-BUHACT@global2024.pydata.org
DTSTART:20241205T123000Z
DTEND:20241205T140000Z
DESCRIPTION:LLMs offer powerful capabilities\, but deploying them effective
 ly in production remains a challenge for conversational AI and Chatbot app
 lications\, especially when it comes to minimizing hallucinations and ensu
 ring accurate responses. In this 90-minute hands-on tutorial\, we’ll exp
 lore building conversational AI systems using CALM and Rasa. CALM (Convers
 ational AI Language Model) combines traditional conversational AI techniqu
 es with LLMs\, separating conversational ability from business logic execu
 tion to deliver reliable\, cost efficient\, and scalable solutions. Unlike
  LLMs that handle both sides of the conversation\, CALM focuses on user un
 derstanding with predefined business logic.  This approach not only accele
 rates development but also enhances cost efficiency\, scalability and reli
 ability. By focusing on predefined business logic with CALM\, you’ll gai
 n the ability to build sophisticated\, scalable systems faster. You’ll a
 lso learn how to use fine-tuned\, open-weight models\, such as llama 8b to
  power your AI assistant.\n\nParticipants will learn how to use CALM for b
 usiness logic and Rasa for dialogue management\, with practical insights\,
  code examples\, and best practices. Materials will be provided via a GitH
 ub repository with a GitHub Codespace for easy access and execution.
DTSTAMP:20250709T220251Z
LOCATION:AI/ML Track
SUMMARY:Building an AI Travel Agent That Never Hallucinates - Alan Nichol\,
  hugo bowne-anderson\, Justina Petraitytė
URL:https://global2024.pydata.org/cfp/talk/BUHACT/
END:VEVENT
END:VCALENDAR