Agent Based LLM Applications: Separating the Hype from Practical Applications

There is significant excitement about Large Language Models, but the hype continues to outpace the reality.  The latest entry into the AI lexicon that is getting increasing attention is that of agent-based approaches where autonomous agents operate and make decisions without human intervention.  While this framework has promise in the future, and some thought leaders project billions of agents operating for organizations and individuals, there are some challenges that current approaches need to overcome before widespread adoption of more ambitious visions of highly functional, safe, reliable “agents for all” can be realized. 

Can't make it?

Register today, and EIS will send you a recorded copy. 

VIEW RECORDING
 

Topics We'll Cover

What kinds of processes can LLMs automate?

Discover how LLMs can streamline workflows by automating tasks like customer service, content creation, data analysis, and personal assistant functions, reducing the need for human intervention in repetitive processes.

The differences between Chatbots, Assistants, and Agents

Understand the distinctions between chatbots, assistants, and agents, from simple rule-based systems to advanced autonomous entities capable of complex decision-making and independent operation.

Templated Prompts: Incorporating additional context

Learn how to enhance the accuracy of LLM outputs by using templated prompts with additional context, ensuring more relevant and precise responses tailored to specific needs.

What is an agent-based approach?

Explore the concept of agent-based approaches where autonomous software agents independently perform tasks, make decisions, and adapt to new situations, inspired by natural systems.

How do agent-based approaches differ from typical LLM-powered applications?

Examine the key differences between agent-based systems and typical LLM applications, focusing on the dynamic, real-time problem-solving capabilities of autonomous agents versus static LLM interactions.

How can agent-based approaches be used for data remediation?

Discover strategies for using agent-based methods in data remediation to identify, correct, and prevent data quality issues, ensuring accurate and reliable information.

Media Partner

VKTR (pronounced vector) Logo

VKTR (pronounced vector) is your guide to AI @ work. Sign up today, for free. 

 
Seth-Earley-CEO-Earley-Information-Science

Meet The Speaker

Seth Earley

Founder & CEO
Earley Information Science

An expert with 20+ years experience in Knowledge Strategy, Data and Information Architecture, Search-based Applications and Information Findability solutions.

Seth has worked with a diverse roster of Fortune 1000 companies helping them to achieve higher levels of operating performance by making information more findable, usable and valuable through integrated enterprise architectures supporting analytics, e-commerce and customer experience applications.

Meet The Speaker

Sanjay Mehta

Principal Solution Architect, Earley Information Science

Sanjay has over two decades of hands-on experience with hundreds of customers for search/analytics, ml/ai, and commerce. He has held a number of strategic roles with renowned vendors such as Lucidworks, Reflektion, Oracle, NetSuite, Endeca, and ATG. His focus is on incorporating enterprise information architecture with ML/AI to deliver practical user experiences that generate tangible value.