Global Director of AI and Data Science
Fortune 100 Pharma CompanyHead of AI Research
Domyn
Building & Evaluating Agentic AI Systems is a practical, end-to-end program focused on designing, building, monitoring and evaluating Agentic AI systems that work reliably in real-world settings.
With live instructor-led sessions, 10 Guided Projects and 5 Mini Project Assignments, you will learn how to work with large language models (LLMs) and add in custom context with prompt engineering and retrieval-augmented generation (RAG). Next, you will focus on designing and building single-agent and multi-agent systems using industry standard frameworks and languages including Python, LangGraph & LangChain.
You will also learn standard design patterns including routing, tool-use, planning, reflection, multi-agent as well as other important components including context engineering, memory and model context protocol (MCP) to optimize and build effective Agentic AI systems.
Finally you will learn how to enable observability (AgentOps) focusing on evaluation, tracing and monitoring using methodologies and frameworks like LLM-as-a-Judge, agentic evals & LangSmith.
You should be comfortable writing code in Python. Prior exposure to Generative AI is helpful but not required. What matters most is that you can code and understand core programming concepts.
Arun Prakash Asokan, an award-winning AI thought leader and Intrapreneur, has been awarded and honoured as Top Gen AI Leader 2024 by Analytics Vidhya, Scholar of Excellence from ISB Hyderabad, and Grand Global Winner of the Tableau International Contest. He holds a Master’s in Computer Science Engineering from BITS Pilani, a B.Tech. in Computer Science & Engineering, and has completed the Advanced Management Program from Indian School of Business, Hyderabad. He has also been honored at global enterprise forums for his groundbreaking AI innovations.
With close to 17 years of experience across all fields of AI, including 7 years at a leading Fortune 100 Pharma Company, Arun currently leads global AI programs driving enterprise-wide adoption of cutting-edge AI and GenAI solutions. Known as a strategic AI translator, he bridges business vision with technical execution, delivering transformative, scalable solutions that have won global recognition.
Bhaskarjit Sarmah is the Head of Financial Services AI Research at Domyn, where he leads cutting-edge work on foundation models, knowledge graphs, and AI governance for regulated industries. Prior to Domyn, he spent over six years at BlackRock, where he founded and led the RQA AI Labs. His research has been featured at NeurIPS and ACM ICAIF, and he has been recognized among the Top 5 Generative AI Leaders in India. A passionate educator and speaker, Bhaskarjit is known for bridging deep AI research with practical, responsible, and enterprise-ready innovation.
Seeking hands-on Agentic AI experience with LangGraph & LangChain
Strengthening portfolios with end-to-end projects
Applying GenAI & Agentic AI to real-world business problems
5 hours/week
10 Guided Projects
5 Mini-Project Assignments
Discussion forum
Weekly discussions & QA
Lifetime access
All session materials
Course completion certificate
12 Live Sessions • 30 Learning Hours • 10 Guided Projects
7 – 11 Mar 2026
Join in to discuss and ask any questions on the content or projects covered in Week 1. We will also release the solution code for Mini Project 1 Assignment and discuss it briefly during this time
The Vision Behind AI Accelerator Program

The AI Accelerator Program is a short, live, cohort-based, instructor-led program designed to upskill professionals in AI through hands-on learning. Within this program, we offer specialized tracks, such as Building and Evaluating Agentic AI Systems, where you'll focus on mastering specific AI skills. You'll learn live with a small group, interact directly with the instructor, and work on real-world projects rather than just watching pre-recorded videos.
This program lasts for 6 weeks, with 5 hours live sessions and 1 hour optional office hour per week, making it manageable alongside your regular job.
You will learn how to: 1. Work with LLMs using prompt engineering and RAG 2. Build single-agent and multi-agent systems using Python, LangChain, and LangGraph 3. Apply common agent patterns such as routing, tool use, planning, and reflection, along with context engineering, memory, and MCP 4. Add observability with a focus on evaluation, tracing, and monitoring, including approaches like LLM-as-a-judge and tooling such as LangSmith
The program is focused on building, monitoring, and evaluation. It is not positioned as a deep dive into production deployment and platform engineering (for example, full LLMOps pipelines, hosting, scaling, and enterprise deployment patterns).
Yes, the program includes 10 guided projects and 5 assignments. Each week, projects will be guided, and solutions for assignments will be provided during office hours. You’ll receive feedback, clarification, and support to ensure you stay on track throughout the program.
It’s fully live. All sessions are conducted in real time on Zoom, with fixed schedules and active participation expected.
This program is for people who want a hands-on, project-driven path to learn how to design and build RAG and agentic systems using Python and popular frameworks like LangChain and LangGraph.
This program is not a fit if you are not comfortable coding in Python (you do not need prior GenAI experience, but you do need solid programming basics). It is also not ideal if you are looking for a purely theoretical course with minimal hands-on work, since the program is built around live sessions, guided projects, and mini projects.
Yes. Hands-on work is designed around Python in Jupyter Notebooks using Google Colab. When paid APIs are required, OpenAI keys are provided for the duration of the course (when needed). The program also references common tools used in real builds (for example, vector DBs and evaluation tooling), so you get practice with an ecosystem you can reuse at work.
Yes! Upon successful completion of all assignments, you’ll receive a Certificate of Achievement. This certificate validates your hands-on expertise in applying AI concepts in practical settings.
Absolutely! This particular program is designed to equip you with the skills to build and evaluate Agentic AI systems, which you can immediately apply to your current projects or job responsibilities.
If you miss a live session, don’t worry! You’ll receive the recordings and resources used in the session as downloadable files, which you can keep and watch at your convenience. You’ll have 1 month to download the recordings and resources from the date the link is shared. However, we encourage you to attend live to maximize engagement and learning.
Yes, we offer a 7-day money-back guarantee. The 7-day period starts on Day 1 of your cohort and ends one day before the third live session. If you’re not satisfied with the program within this window, you can request a refund by contacting our support team at [email protected]. T&Cs.
While the schedule and curriculum are typically fixed, in exceptional circumstances, there may be adjustments. Any changes will be communicated in advance, and we’ll ensure that they don’t affect the core learning objectives. Our main goal is to provide you with a seamless, hands-on learning experience, and we’ll work to maintain that, no matter the adjustments.