From Prompt to Production: Agent-Based LLMs for Data Analysis and Fixing Software and Data Visualization Bugs

Recent advancements in Large Language Models (LLMs) have significantly enhanced automation across a diverse range of tasks. These agents have the ability to use tools, execute commands, analyze feedback from their environment, and plan future actions.
 
This session explores how autonomous LLM agents can take on tedious tasks, such as debugging, patching, and resolving data visualization bugs, allowing teams to focus on high-value work like building models, generating actionable business insights, and developing innovative software more efficiently. Learn how these agents can interact with enterprise data through natural language to provide real-time insights, while multimodal capabilities enable them to tackle the diverse challenges of complex data visualization issues.
 
The Why:
As software and data-driven applications scale, debugging and fixing bugs and visualization issues remain some of the most time-consuming and repetitive tasks for engineers. Traditional debugging requires manual intervention, slowing down workflows and delaying production releases. With the rise of LLM-powered agents, teams now have access to autonomous systems capable of identifying, analyzing, and resolving errors with minimal human oversight.
 
Key Takeaways:

• Learn how LLM agents interact with tools to troubleshoot and fix issues.
• Discover practical examples of LLM agents in action, handling real debugging scenarios and data visualization.
• Learn how to use multimodal capabilities in LLM agents to process and resolve issues through text, image, and code-based reasoning.

This session is for... technical professionals who want to gain a competitive edge by incorporating LLM-powered agents into their workflow.