Explains the importance of defining orchestration boundaries in enterprise LLM applications, focusing on architecture decisions over framework choices.
The New York Times uses a custom AI tool called the 'Manosphere Report' to track and analyze podcast content for journalistic coverage.
Explores AI agents, their core components, differences from LLMs, and real-world applications, positioning them as the future of autonomous AI systems.
Final notes from a book on LLM prompt engineering, covering evaluation frameworks, offline/online testing, and LLM-as-judge techniques.
A framework for building data flywheels to dynamically improve LLM applications through continuous evaluation, monitoring, and feedback loops.
A reflection on how LLMs have simplified AI prototyping compared to traditional ML, but may lead to similar deployment disappointments.
A practical guide sharing lessons learned from a year of building real-world applications with Large Language Models (LLMs).
A tutorial on building and deploying an LLM-based AI application using Prompt Flow in Visual Studio Code, from setup to containerization.
A guide to selecting the right LLM architectural patterns (like RAG, fine-tuning, caching) to solve common production challenges such as performance metrics and data constraints.
Explores the difference between rigorous prompt engineering and amateur 'blind prompting' for language models, advocating for a systematic, test-driven approach.
