Agentic AI in Production Sahaj Software

DEVDAY_

Agentic AI in Production

Karthika Vijayan, Shruti Prasanna Dhavalikar, Yahya Poonawala, Sujit Kamthe, Suman Paul Choudhury, Amit Bhagat, Vinayak Kadam, Harshad Nawathe, Sandipan Dandapat

1 November 2024

Koregaon Park, Pune

View Location

About the Event

Agentic AI in Production is a one-day conference bringing together practitioners who have built, tested and evolved agentic systems beyond the prototype stage.

Through real-world systems and hard-earned lessons, the sessions explore architecture, multi-agent coordination, reliability, evaluation, memory, observability and performance.

The focus is not on what agents could do, but on the decisions, failures and patterns that determine whether they actually work in production.

Join us in Pune for a practitioner-led day on building dependable Agentic AI systems at scale.

Agenda of the Day

ㅤ

Keynote: Safe and Inclusive AI for a Multilingual and Multicultural World (9:40 AM – 10:25 AM)
Speaker: Prof. Sandipan Dandapat

As AI systems become increasingly capable and agentic, ensuring they are safe, responsible, and inclusive becomes critical. This talk explores two complementary dimensions of trustworthy AI: evaluating safety, biases, and stereotypes in large language models, and improving multilingual reliability through linguistically informed testing and agentic approaches to performance prediction. Together, these research directions highlight how we can build AI systems that are not only more powerful, but also safer and more inclusive across languages and communities.

Session 1: Shift-left Considerations in Agentic AI (10:30 AM – 11:10 AM)
Speaker: Dr. Karthika Vijayan

Agentic system design starts with getting the mental model and problem scope right, rather than jumping straight into agents and orchestration. This talk presents a shift-left approach to thinking about agentic systems, with capability, accuracy & consistency, performance, and modularity considered from the outset. The goal is to build the right system for the problem while anticipating the constraints that will shape it as it grows.

Break (11:10 AM – 11:25 AM)

Session 2: Engineering Agents Beyond the Happy Path (11:30 AM – 12:10 PM)
Speaker: Shruti Prasanna Dhavalikar

Building an agentic solution for a large enterprise platform comes with a unique requirement, to build not one assistant, but a reusable framework that supports multiple use cases. This talk walks through the design and evolution of that system from three angles: performance, how a working-but-slow orchestrator design is rebuilt; configurability and reusability, how modularity allows the framework to be repurposed for multiple use cases with shorter time-to-market; and robustness, what evaluations do and do not catch.

Session 3: My Agents Can’t Agree and Now It’s an Architectural Problem (12:15 PM – 12:55 PM)
Speaker: Yahya Poonawala

As natural language semantic complexity increases for an application, building reliable agentic systems becomes more challenging. This talk explores the evolution of a digital advertisement campaign planning assistant from a nominal orchestrator-worker system to an NLP-incorporated, consistency-assured multi-agentic system.

Lunch Break (12:55 PM – 2:00 PM)

Session 4: Lessons from an Agentic AI Raga-Metal Band (2:05 PM- 2:55 PM)
Speaker: Sujit Kamthe

This talk explores how eleven specialist agents collaborated to compose raga-metal fusion music using advanced agentic patterns for coordination, critique and verification. Through shared-blackboard collaboration, evaluator-optimizer loops, deterministic verification, LLM-as-a-judge and bounded multi-agent debate, the talk differentiates what belongs in code, what requires model judgement and how agents should be decomposed around decisions.

Session 5: Who Watches the Agent? Engineering Trust into Autonomous AI (3:00 PM – 3:40 PM)
Speaker: Suman Paul Choudhury

Building an AI agent is easy. Trusting one in production is not. This talk explores the harness needed to bridge that gap, from evaluating multi-step agent behavior and enforcing guardrails to making agents observable, debuggable and reliable. Based on the latest research in agent reliability, we will look at the practical systems and techniques that turn autonomous agents from unpredictable prototypes into trustworthy production systems.

Lightning Talk: Principles & Strategies for Agent Memory (3:45 PM – 4:00 PM)
Speaker: Amit Bhagat

Building a basic agent is easy; giving it reliable memory is hard. As interactions grow, naive state management inevitably leads to surging token costs, latency spikes, and “context blindness”. This talk focuses on the principles of agent state and memory management, and describes and evaluates top strategies to do so.

Break (4:00 PM- 4:15 PM)

Lightning Talk: How Hidden Prompt Breaks Production LLMs (4:20 PM – 4:35 PM)
Speaker: Vinayak Kadam

When LLM-powered applications break in production, engineering teams usually audit system prompts or blame upstream model updates. However, system prompts are only half the instruction; the dynamic annotations, schema descriptions, and few-shot payloads injected at runtime carry equal weight. This talk uncovers the hidden failure modes of data-prompt coupling, examines common anti-patterns and covers practical strategies to retain alignment.

Birds of a Feather: Surviving Prompt Drift and Context Bloat (4:40 PM – 5:20 PM)
Speaker: Harshad Nawathe

Meet our Speaker(s)

Karthika Vijayan

Solution Consultant

Dr. Karthika Vijayan has been conducting research in the field of conversational AI with voice and text data for almost a decade. Her research has been published in several journals and presented at various international conferences. Prior to joining Sahaj, Dr. Vijayan worked as a research fellow in the Department of Electrical and Computer Engineering at the National University of Singapore. She also worked as research associate in the Department of Electrical Engineering at the Indian Institute of Science, Bangalore. She obtained her PhD in Speech Signal Processing from the Department of Electrical Engineering at the Indian Institute of Technology Hyderabad in 2016. She is an active member of IEEE, ACM and APSIPA.

Shruti Prasanna Dhavalikar

Solution Consultant

Shruti Dhavalikar is a skilled Data Scientist with over 7+ years of experience in the field. With a deep passion for data science and a strong understanding of data patterns, she successfully delivers end-to-end product cycles as well as actively contributes to research projects. She has published and presented research works at several international conferences.

Yahya Poonawala

Solution Consultant

Yahya Poonawala is a technology professional with over 13 years of experience in software engineering, architecture and engineering leadership. Having worked across product and services organisations, Yahya brings a problem-driven approach to system design, with a keen interest in building scalable, reliable and reusable software systems. His current work at Sahaj focuses on applying these principles to complex engineering challenges, including agentic AI systems.

Sujit Kamthe

Solution Consultant

Sujit is an engineering leader, software architect and AI practitioner with more than 16 years of experience building distributed systems, cloud platforms and enterprise applications, and building high performing engineering teams. His current work focuses on production-grade agentic AI, cloud-native architecture and AI-assisted software engineering. He writes and speaks about software architecture, engineering practices, developer productivity and the changing role of engineers.

Suman Paul Choudhury

Solution Consultant

Suman Paul Choudhury is a Data Science Consultant at Sahaj with over 10+ years of industry experience in AI and Machine Learning. His work spans Generative AI, Computer Vision, AdTech, customer analytics and large scale ML systems.Suman has extensive experience working with technologies such as PySpark, deep learning, graph based machine learning, LLMs, LangGraph and modern MLOps ecosystems.He holds a Master’s degree in Signal Processing, has contributed to IEEE research publications and has patent involving vision assisted checkout systems.Suman is particularly passionate about translating complex AI concepts into practical systems that solve real business problems and about helping teams move from AI experimentation to scalable, production ready solutions.

Amit Bhagat

Solution Consultant

Software Engineer at Sahaj with experience spanning high-throughput telemetry platforms, agentic AI systems, and distributed data engineering. Brings a strong foundation in building resilient backend systems, real-time event-streaming architectures, and cloud infrastructure.

Vinayak Kadam

Solution Consultant

Vinayak Kadam is a Solution Consultant at Sahaj Software, where he works on AI-powered and multi-agent systems. With experience spanning data engineering, cloud platforms, and large-scale distributed systems, he focuses on building production-ready solutions that combine intelligent automation with practical business outcomes.

Harshad Nawathe

Solution Consultant

Harshad has over 16 years of experience building scalable software, distributed systems, and data products. With a background deeply rooted in core software engineering and agile practices, he is currently helping large enterprises on AI enablement and legacy system modernization.

Sandipan Dandapat

Associate Professor at IIT Hyderabad

Sandipan Dandapat is an Associate Professor at IIT Hyderabad with over 20 years of experience in NLP and Generative AI. Prior to joining academia, he spent more than a decade at Microsoft Research India and Xerox Research Centre India, contributing to research in multilingual NLP and machine translation. He holds a Ph.D. from Dublin City University and a Master's degree from IIT Kharagpur. He actively contributes to the NLP research community through academic service, including senior area chair and area chair roles at conferences such as EMNLP and NAACL, and Program Chair for the Panini Linguistics Olympiad and CODS. With an emphasis on building robust, inclusive, and equitable language technologies, his current research spans Generative AI, NLP, multilingualism, language model evaluation, and responsible AI.