Learn Generative AI from someone who uses it every day.
Practitioner-led, project-first learning in LLMs, RAG and agentic AI, built around real problems, not textbook exercises.
Rishav Kumar teaches Generative AI, LLMs, prompt engineering, RAG and agentic AI as Head Instructor at Skillancy, Instructor at NextLeap and Visiting Faculty at Scaler. Sessions are live and hands-on, and learners build working AI applications rather than just watching demos.
Focus areas
Platforms & roles
Skillancy
Live, mentor-led cohorts where learners build real AI products: RAG apps, LLM workflows and agentic automations they can show in interviews.
View programs at skillancy.in →NextLeap
Teaching and mentoring fellows through hands-on analytics, from first SQL query to a graduation project that's ready for a portfolio.
- Data Analyst Fellowship
- Business Analyst Fellowship
Scaler
Masterclasses for Scaler's Online PGP in Business and AI, showing how AI strategy plays out inside one of the world's largest retailers.
- Masterclass: AI strategy & personalisation
The AI Strategy Behind Retail Orgs' Personalised Shopping Experience
A 90-minute session on how large retailers use data and AI to personalise shopping at scale, covering the business problems, the models and the metrics that show it's working.
300+ working professionals built their first AI agent in 60 minutes
A hands-on session for people who had held off on learning AI because it seemed too technical. Everyone left with a working agent of their own. I also run free webinars on how AI skills turn into better roles and faster promotions.
Built to make you job-ready, not just certified.
Build, don't watch
Every session ends in something that works: a prompt pipeline, a RAG app or an agent you can show.
Real problems
Examples come from the kind of business problems I work on at Walmart scale, not toy datasets.
Think, then tool
Frame the decision first, then pick the model, the retrieval and the agent design that serve it.
Generative AI terms, explained simply
- Generative AI
- AI systems that create new text, images, code or audio based on patterns learned from large amounts of data.
- Large language model (LLM)
- A neural network trained on large amounts of text to understand and generate language. LLMs power tools such as ChatGPT, Claude and Gemini.
- Prompt engineering
- Designing instructions, examples and output formats so an LLM produces reliable, useful results.
- Embeddings
- Numeric vectors that represent the meaning of text, so similar ideas sit close together. They are the basis of semantic search.
- Vector database
- A database that stores embeddings and quickly finds the items most similar in meaning to a query.
- Retrieval-augmented generation (RAG)
- A technique that retrieves relevant passages from your own data and gives them to an LLM, so answers are grounded in real sources and can cite them.
- Fine-tuning
- Training a model further on examples to change its behaviour, style or task performance. LoRA and PEFT do this by updating only a small set of parameters.
- AI agent
- An LLM-powered system that plans steps and uses tools such as search, APIs or databases to complete a task, rather than only answering a question.
- Agentic AI
- Designing AI systems around agents that reason, act and iterate towards a goal with limited human input.
- Multi-agent orchestration
- Coordinating several specialised AI agents that divide a task and hand work to each other.
- LLM evaluation
- Measuring the quality of AI output, such as accuracy, groundedness and hallucination rate, using test sets and techniques like LLM-as-judge.
- Guardrails
- Checks around an AI system that block unsafe inputs and outputs, including prompt-injection defences, content moderation and privacy filters.
Teaching FAQ
Where does Rishav Kumar teach?
Rishav Kumar is Head Instructor at Skillancy, where he teaches live cohorts in Generative AI, agentic AI and data; an Instructor and mentor at NextLeap for the Data Analyst and Business Analyst fellowships; and Visiting Faculty at Scaler, where he delivers masterclasses for the Online PGP in Business and AI.
Which Generative AI topics does Rishav Kumar teach?
He teaches LLM fundamentals and prompt engineering, retrieval-augmented generation (RAG) with embeddings and vector databases, agentic AI including tool use and multi-agent workflows, evaluation and guardrails, and deploying AI applications.
Do I need coding experience to learn Generative AI with Rishav Kumar?
It depends on the format. Founder workshops and leadership briefings need no coding. Hands-on bootcamps and cohort programs assume basic Python, which is refreshed at the start.
Are Rishav Kumar's sessions live?
Yes. His cohorts, workshops and masterclasses are taught live, with hands-on building in every session.
Want me to teach your cohort or community?
Guest lectures, masterclasses and multi-week programs on Generative AI, LLMs, RAG and AI agents.