🚀 Advanced Prompting Techniques: Maximizing LLMs in Production 🎉

Join us for a hands-on, interactive session designed for developers and AI enthusiasts ready to level up their prompting skills. This event is packed with practical insights, live coding, and expert guidance to help you take your AI applications from good to great.

This session is part of our “AI in Production” series — bringing together builders, innovators, and enthusiasts to explore the frontiers of applied AI.

📅 Event Details

• When: December 19, 2024 (Thursday)
• Time: 2:00 PM - 5:00 PM
• Where: AWS 19th floor (Come up to this floor!) 525 Market St, San Francisco, CA 94105

🚀 Agenda

• 2:00 PM - 2:15 PM: Welcome and Introductions
• 2:15 PM - 4:00 PM: Live Session: Advanced Prompt Engineering
  • Improve Accuracy: Techniques to reduce hallucinations and achieve precision.
  • Enhance Consistency: Best practices for stable outputs every time.
  • Reduce Latency: Speeding up AI pipelines in real-world scenarios.
  • Eval Techniques: From LLM judgments to external evaluators, what works?
  • Deep Dive: Why non-determinism persists even when temperature == 0?
  • Scaling Prompt Management: Tools and workflows for handling hundreds of prompts.
  • Semantic Streaming: The future of token-based outputs.
• 4:00 PM - 4:30 PM: Q&A + Discussions
• 4:30 PM - 5:00 PM: Networking

👨‍💻 Meet the Speaker

Vaibhav Gupta

LinkedIn | BAML GitHub

Vaibhav is an member of Seattle AI Tinkerers community and helps with organizing events there. He’s also one of the creators of BAML, an open-source programming language for structured AI outputs. With nearly a decade of experience at companies like Google, Microsoft, and D. E. Shaw, he specializes in optimizing AI performance and loves demystifying complex concepts in generative AI.

Who Should Attend? 🤖

This session is curated for AI developers, data scientists, and engineers who:

• Are actively building or managing AI pipelines.
• Have worked programmatically with LLM APIs or structured outputs.
• Want to scale AI solutions effectively and understand advanced techniques.

Bring Your Laptop: Code along with live examples and leave with practical tools.

About Boundary & AWS GenAI Loft

Boundary: The creators of BAML, an open-source language designed to make LLMs more reliable and structured, empowering developers to build robust agents, chatbots, RAG systems, and more.

​AWS Gen AI Lofts AWS GenAI Lofts are collaborative spaces and immersive experiences for startups and developers.

⭐️ Why Attend?

Whether you’re tackling inconsistency in LLMs, managing prompt scalability, or looking for the latest on semantic streaming, this session is for you. Gain actionable insights, connect with like-minded peers, and explore the future of generative AI development.

What is The AI in Production Series?

We’re all AI Tinkerers, but at heart, but at some point the project has to go live. This series is about tackling and discussing those challenges in depth, from how to switch and test models, or to measure cost, all the way to which research is worth investing in. These events are centered around in-depth technical talks and often are live workshops.

See you there! 🚀