Developersummit
  • HOME
  • SPEAKERS
  • SESSIONS
  • SCHEDULE
  • FAQ
  • BUY TICKETS
  • ONDEMAND
  • CONTACT
saltmarch

GIDS news media, articles, insights and virtual events educate and illuminate its audiences so they can be fully prepared to deal with the new realities at work and in their professions.

Saltmarch On-Demand
Media

Our Experts

Videos On Demand

Insights

Call for Papers

Connect

About Us

Privacy Policy

Terms & Conditions

Contact Us

Subscribe to Developersummit

Get the latest event updates, and insights from today's leading voices.

© 2026-2027 Saltmarch. All rights reserved.

Agentic RAG in Production: Orchestration, Evaluation, and ROI
RegisterTwitterLinkedInFacebook

< session />

Agentic RAG in Production: Orchestration, Evaluation, and ROI

Wed, April 22 at 3:10 PM - 4:10 PM GMT+5:30DeepTech DataTech

Many RAG initiatives stall after early demos because they hallucinate, break under orchestration, or fail to show measurable business value. This session introduces Agentic RAG, where retrieval decisions, evaluation, and improvement are handled by agents embedded in enterprise workflows. The session explains how Salesforce Agentforce, Salesforce Data Cloud, and LangGraph can be combined to build grounded, self correcting RAG systems. It also covers how to apply evaluation frameworks such as the RAG Triad, TruLens, and Ragas to measure accuracy, fairness, and ROI. The session concludes with a live Smart Checkout Helper scenario that demonstrates grounded retrieval, agent driven correction, and quantified business impact.

What you will Learn

  • How to design Agentic RAG systems that coordinate retrieval, reasoning, and decision making across enterprise workflows

  • How to evaluate RAG quality using context, groundedness, relevance, and continuous validation frameworks

  • How to connect RAG metrics to business outcomes such as conversion lift, call deflection, and AHT reduction

Who Should Attend

  • Software Developers building AI enabled applications

  • Architects designing production grade RAG and agent systems

  • Data and AI Engineers responsible for grounding and evaluation

  • Technical Leads and Engineering Managers focused on reliability, governance, and ROI

< speaker_info />

About the speaker

Rohit Bhardwaj

Rohit Bhardwaj

Director of Architecture, Expert in Cloud-native Solutions

Rohit Bhardwaj is a Director of Architecture working at Salesforce. Rohit has extensive experience architecting multi-tenant cloud-native solutions in Resilient Microservices Service-Oriented architectures using AWS Stack. In addition, Rohit has a proven ability in designing solutions and executing and delivering transformational programs that reduce costs and increase efficiencies.

As a trusted advisor, leader, and collaborator, Rohit applies problem resolution, analytical, and operational skills to all initiatives and develops strategic requirements and solution analysis through all stages of the project life cycle and product readiness to execution.
Rohit excels in designing scalable cloud microservice architectures using Spring Boot and Netflix OSS technologies using AWS and Google clouds. As a Security Ninja, Rohit looks for ways to resolve application security vulnerabilities using ethical hacking and threat modeling. Rohit is excited about architecting cloud technologies using Dockers, REDIS, NGINX, RightScale, RabbitMQ, Apigee, Azul Zing, Actuate BIRT reporting, Chef, Splunk, Rest-Assured, SoapUI, Dynatrace, and EnterpriseDB. In addition, Rohit has developed lambda architecture solutions using Apache Spark, Cassandra, and Camel for real-time analytics and integration projects.

Rohit has done MBA from Babson College in Corporate Entrepreneurship, Masters in Computer Science from Boston University and Harvard University. Rohit is a regular speaker at No Fluff Just Stuff, UberConf, RichWeb, GIDS, and other international conferences.

Related Talks

Building LLM-Powered Agents with Real-Time Reasoning Loops

Thu, April 23

Building LLM-Powered Agents with Real-Time Reasoning Loops

Apurva Misra
The AI-Native Codebase

Tue, April 21

The AI-Native Codebase

Ragunath Jawahar
Computer Programming is Dead; Long Live AI-First Programming

Tue, April 21

Computer Programming is Dead; Long Live AI-First Programming

Stephen Chin, Cassandra Chin

On-Demand Talks

Custom GPTs for Fun, Profit, and Potential Liability

Custom GPTs for Fun, Profit, and Potential Liability

Kenneth Kousen
AI Powered Root Cause Analysis for Production Alerts

AI Powered Root Cause Analysis for Production Alerts

Deepa Elumalai
Beyond Logs: Real-Time Anomaly Detection with Machine Learning

Beyond Logs: Real-Time Anomaly Detection with Machine Learning

Fawaz Ghali
Word Embeddings - An Alternative and Efficient Approach to Search for Documents

Word Embeddings - An Alternative and Efficient Approach to Search for Documents

Ananth Gundabattula
AI-Driven Transformation in Contact Centers: Enhancing Customer Experience

AI-Driven Transformation in Contact Centers: Enhancing Customer Experience

Nurul Khan
Real-time Skills Forecast: Applying ML & NLP in Qualitative Research Activities

Real-time Skills Forecast: Applying ML & NLP in Qualitative Research Activities

Harri Ketamo
All On-Demand »