Learn to design and deploy AI-powered QA agents in 4 weeks, no coding required. Just n8n, real workflows, and hands-on practice.
Learn to evaluate RAG systems end-to-end. Build evaluation datasets, validate LLM-as-a-Judge against human labels, and set up CI/CD release gates. 4 days of hands-on training.
Framing RAG Evaluation & Defining Quality
Tracing RAG Failures from Source to Answer
Error Analysis & Failure Taxonomies
Golden Datasets, Rubrics & Ground Truth
LLM-as-a-Judge & Automated Evaluators
Retrieval, Grounding & Faithfulness Metrics
Robustness, GraphRAG & Agentic RAG Evaluation
CI/CD Release Gates & Production Evals
Intensive 4 Days
Training
Live Q&A Session
Access to Students group with Instructor
Lifetime Recording Access
Hands-on Exercises
Cheatsheets and More
Join a virtual workshop scheduled at a time convenient for Europe & North America participants!
MODULE 1
Gen AI & Agentic AI Fundamentals
Day 1
MODULE 2
Prompt & Context Engineering
Day 2
MODULE 3
n8n Setup, Essentials & QA Workflows
Day 3
MODULE 4
APIs, Webhooks & Requirement Intelligence Agents
Day 4
MODULE 5
Test Design Agents
Day 5
MODULE 6
Grounded QA Agents & RAG
Day 6
MODULE 7
Job-Ready QA Workflows & AI for Test Automation
Day 7
MODULE 8
Capstone Project
Day 8
Learn how evaluation differs from testing, benchmarking, and monitoring, and work through the Three Gulfs and the Analyze-Measure-Improve cycle. Define evaluation goals, quality dimensions, ground truth, and acceptance criteria. Then follow a RAG request from ingestion through retrieval, reranking, generation, and citation, using traces to find where failures arise.
Inspect real traces, group recurring failures into a failure taxonomy, and build golden, real-world, synthetic, edge and adversarial examples. Create clear rubrics and use reviewer agreement to produce reliable reference labels. Then define metric contracts, build deterministic and semantic checks, and validate LLM-as-a-Judge against human labels.
Evaluate retrieval separately from the final answer using Precision@k, Recall@k, MRR, MAP, and nDCG. Assess answers for correctness, faithfulness, context use, citations, and consistency, and distinguish unsupported answers apart from faithful answers built on wrong or stale evidence. Finish with adversarial stress cases, evaluator red-teaming, GraphRAG, and agentic workflows.
Connect golden regression suites to CI/CD and release gates, and cover offline and online evaluation, human review, judge drift, latency, cost, and reliability. Learn to interpret metrics, communicate uncertainty, and compare baseline versus challenger results. In the capstone, find a RAG failure, apply a fix, rerun evaluations, and present an evidence-backed conclusion.
17+ Years of Experience
Live Workshops
1000+ Students Taught
Toni Ramchandani is the Vice President of Applied AI Engineering at MSCI Inc., bringing over 17 years of experience in AI, data, cloud, and engineering execution. He specializes in enterprise AI agents, RAG, LLM evaluation, and AI observability to turn emerging tech into scalable, production-ready enterprise capabilities.
Toni is also an author, having written A Generative Journey to AI, and an avid endurance athlete who regularly runs, rides, and hikes.
Find Out What The Workshop Offers!
Test Lead at Moolya Testing
It may be a coincidence that I am more focused on what I am learning than I have ever been over the years, but there’s no denying the fact this bootcamp so far has given me several Eureka! moments about Software Engineering and its idiosyncrasies. The syllabus, the teaching style, the design of assignments, the deep discussions, the flexibility, the infrastructure, planning and logistics… almost everything about this camp is path breaking. I have enjoyed every bit of being a part of it.
Senior QA, Qualitest
Vignesh is a learned trainer or educator. He knows the topic so well and had answers to all the questions, his ability to answer each question patiently makes him do justice to his job.
Automation Architect, ACL Digital
This bootcamp has opened an opportunity to make use of GenAI in a very simple yet very effective way for QA day to day tasks.
Software Testing Professional, Evolent
Lead Quality Assurance Enginer
The Agentic AI Bootcamp (Dec 2025) was an outstanding learning experience. The hands-on sessions, real AI workflows, and practical examples helped me understand how Agentic systems operate in real projects. Truly a valuable and future-ready program
QA Consultant
I appreciate the workshop’s structure-it begins with the fundamentals and gradually incorporates practical applications for real projects. The provided resources are also very helpful for practicing alongside the training.
Senior QA Automation Engineer
I feel this bootcamp is really useful for me. I was able to create an agent on own at my company parallely while attending this workshop. As my company also is keen on AI products, this helped me a lot in my own work. I feel more confident in understanding them now
QA Manager
It was a nice start to learn and implement in day-to-day task in QA Life.Definely lots of challenges will be there in Realtime project but this foundation level knowledge will help to overcome.
Manager - Technical Programs
Attending the Agentic AI Bootcamp has been a game-changer for me. I came in completely clueless about Agentic AI, but the way the concepts were broken down and connected to hands-on projects has given me real confidence to start building on my own. The sessions were practical, engaging, and cleared a lot of confusion I had about how AI agents actually work in real scenarios.
Lead QA Engineer
Attending the Agentic AI Bootcamp has been a game-changer for me. I came in completely clueless about Agentic AI, but the way the concepts were broken down and connected to hands-on projects has given me real confidence to start building on my own. The sessions were practical, engaging, and cleared a lot of confusion I had about how AI agents actually work in real scenarios.
This bootcamp helped me understand AI agents in a very clear and practical way. The concepts were explained in simple language with good examples, so I can now see how to use agents in real work.
I find the instructor (Vignesh) is wonderful in engaging the participants, explaining the concepts and addressing the queries
We are also in these cities
Yes, This is a hands-on workshop with a lot of mini-activities that you will have to perform on your laptop. So, To get the best experience for the workshop, We will suggest joining through a Laptop/Computer.
You’ll need basic Python programming skills, familiarity with APIs and JSON, and a basic understanding of how LLMs work, including prompts, context and generated responses. Experience in software testing or test automation is helpful, but you don’t need any prior experience with RAG evaluation.
Yes, people will get added to the Workshop alumni group to take guidance from the instructor and interact with your peers.
Please contact us at [email protected] to get group discounts for your team
Yes, you can get access to the recordings later on if you have a premium pass for the workshop.
We will share the URL to join the workshop prior to the workshop date.
The workshop will be for 4 hours from 5 PM IST to 9 PM IST, on Saturdays and Sundays for 2 Weeks.
The workshop will run for 4 hours, from 5 PM IST to 9 PM IST, on the following dates:
Day 1: October 31 (4 hrs Session),
Day 2: November 1 (4 hrs Session),
Day 3: November 7 (4 hrs Session),
Day 4: November 8 (4 hrs Session).
For attendees in different time zones:
In Central European Summer Time (CEST), the workshop will be from 1:30 PM CEST to 5:30 PM CEST.
In Eastern Time (EDT), the workshop will be from 7:30 AM UTC to 11:30 AM EDT.
By entering your email, you agree to receive related marketing emails as described in our Privacy Policy. You can unsubscribe anytime.
