The ODSC East 2025 will feature top experts discussing the impact of AI on software development and application. Robert Brennan will address the practicalities of using autonomous coding agents in software engineering, providing insights on leveraging AI while avoiding pitfalls. Aditya Palnitkar highlights the necessity of stringent evaluation systems for LLMs to boost their development and performance, while Vivek Muppalla underscores the complexities involved in creating reliable LLM agents for enterprises, focusing on the importance of balancing accuracy, safety, and scalability in their architecture.
AI is reshaping software development, but autonomous coding agents like Devin and OpenHands raised questions about their effectiveness versus human developers.
Testing and monitoring LLMs are often overlooked - but critical to improving performance and development speed. A world-class evaluation system can accelerate your LLM projects.
Creating high-performance LLM agents for enterprise use is challenging, especially when balancing accuracy, safety, and scalability in the decision-making process.
Collection
[
|
...
]