Presenter: Pradnya Desai, Senior Technical Architect at Salesforce.
Moderator: Nujhat Tasneem, Device Engineer, Intel.
Abstract: Large Action Models, designed for function calling, reasoning, and planning. These models are designed to streamline and simplify the integration of AI into your workflows, reducing the complexity often associated with LLMs. Unlike LLMs, which are fantastic at generating text and responses, LAMs go a step further by proactively managing entire workflows without needing explicit instructions for each task. Imagine a CRM system that not only knows what you want but also anticipates your needs, automating processes and making informed decisions on your behalf. This is where LAMs shine, drawing from their roots in fields like robotics, autonomous vehicles, and gaming AI, where understanding context and making real-time decisions are crucial.
This session will cover the overview of Salesforce AI Research’s xLAM the Large Action Models and it’s utilization in Agentic AI. These models are designed for function calling, reasoning, and planning. These models are streamlined and they will simplify the integration of AI into the workflows, reducing the complexity often associated with LLMs.
Presenter’s Bio:
Senior technical architect specializing in analysis, design, development of cross cloud solutions using Salesforce platform – Sales Cloud, Service Cloud, Experience Cloud. Experience in Agentforce, Agentic AI, Digital Engagement, Amazon Connect, Omni Channel, Omni Studio, Financial Service Cloud. Expert in implementation of REST Services, Middleware Applications, OSB – SOA and related technologies. Pradnya has 22+ years of Experience in application development and 8+ years of experience in the Salesforce Ecosystem.
