Technology professionals developing generative AI applications are finding that there are big leaps from POCs and MVPs to production-ready applications. They're often developing using prompting, Retrieval Augmented Generation (RAG), and fine-tuning (up to and including Reinforcement Learning with Human Feedback (RLHF)), typically in that order. However, during development – and even more so once deployed to production – best practices for operating and improving generative AI applications are less understood.
Join industry authorities Dr. Greg Loughnane and Chris Alexiuk in this exciting webinar to learn all about:
- How to design and implement production-ready systems with guardrails, active monitoring of key evaluation metrics beyond latency and token count, managing prompts, and understanding the process for continuous improvement
- Best practices for setting up the proper mix of open- and closed-source tooling, understanding the iterative sequence of improvement steps needed to achieve better LLM outputs, and identifying and remediating the skills gaps that exist within your engineering and data science teams
- Demonstrating the most anticipated end-to-end tool – LangSmith (still in beta) – that is trying to solve this entire suite of production problems for companies interested in building, deploying, and optimizing complex LLM applications
You don't want to miss out! Register today to save your seat!
December 6th, 2023 at 11:00am PST, 2:00pm EST, 7:pm GMT
Brought to you by: