Agentic AI & RAG
A 12-week beginner course: build AI assistants that search documents, cite sources, admit when they don't know, and ask for approval before acting.
Curriculum
ANC-01Python for AI Builders4 lessons · 16 h
- Variables, strings, lists and dictionaries
- Functions and JSON
- Building a keyword FAQ bot
- Your first LLM API call
ANC-02Talking to LLMs4 lessons · 16 h
- Tokens and multilingual cost differences
- System prompts, temperature and few-shot examples
- Schema-valid JSON output
- Per-field accuracy evaluation
ANC-03Embeddings & Your First RAG5 lessons · 16 h
- Embeddings for comparing meaning
- Chunking documents
- Chroma vector database
- Prompts that force citations and honest refusals
- English and Hindi questions on one index
ANC-04Better RAG, Measured5 lessons · 16 h
- Evaluation sets and recall@k
- BM25 keyword search
- Hybrid search with rank fusion
- Cross-encoder reranking
- LLM judge for faithfulness and its biases
ANC-05Agents: Tools, Loops & MCP5 lessons · 16 h
- Hand-written agent loop with step limits and traces
- Approval gates for actions
- Prompt-injection attack and defence
- The same agent in LangGraph
- Tools published over MCP
ANC-06Agentic RAG, Deployment & Capstone5 lessons · 16 h
- Self-grading retrieval with query rewriting
- Human-in-the-loop pauses
- Token and cost logging
- FastAPI endpoint
- Capstone project review
What's included
Questions
Do I need prior experience?
This course is set at beginner level. The first module starts from the basics, so you only need the time and a laptop or phone with a stable connection.
What if I miss a live class?
Every live class is recorded and posted within 24 hours. You keep access to the recordings for 12 months.
When are the classes?
The next cohort starts 9 November 2026 and runs for 12 weeks, ~8 hrs per week. The full timetable and class link appear in My courses before the first class.
Which language is the course taught in?
English.
How do I pay?
Online through UPI, cards, net banking or wallets, processed by Razorpay. You get a receipt by email and the course appears in My courses right away.
Q01What is retrieval-augmented generation, and why use it?RAGBasic
RAG retrieves relevant passages from your own documents at question time and puts them in the prompt, so the model answers from that text.
It gives the model current and private knowledge without retraining, lets you show citations, and reduces made-up answers.
Q02What are embeddings?EmbeddingsBasic
Embeddings are vectors that represent the meaning of text. Texts with similar meaning end up close together, usually measured with cosine similarity.
They power semantic search: you embed the question and find the nearest document chunks.
Q03How do you choose a chunk size?RAGIntermediate
It is a trade-off. Small chunks match precisely but lose surrounding context. Large chunks carry context but dilute relevance and use more tokens.
A common start is a few hundred tokens with some overlap, split along the document's own structure such as headings. Then measure retrieval on real questions and adjust.
Q04What are hybrid search and reranking?RetrievalIntermediate
Hybrid search combines keyword search (BM25) with vector search, so exact terms such as product codes or names are not missed.
A reranker, usually a cross-encoder, then rescores the top candidates against the question, and only the best few go to the model.
Q05How do you evaluate a RAG system?EvaluationIntermediate
Evaluate retrieval and generation separately.
For retrieval, build a labelled set of questions and measure whether the right passage appears in the top k results. For generation, check faithfulness to the retrieved context, correctness and citation accuracy, using human review or a model-graded check that you have calibrated against human judgements.
Q06How does tool use (function calling) work?AgentsIntermediate
You describe each tool with a name, a description and a JSON schema for its parameters. The model returns a structured request to call a tool.
Your code runs the tool and sends the result back, and the model continues. The model never executes anything itself, so your code controls what is allowed.
Q07How does an agent loop work, and how do you stop it running away?AgentsAdvanced
The model chooses an action, your code runs the tool, the result is added to the conversation, and the loop repeats until the model gives a final answer.
Controls: a maximum number of steps, token and cost budgets, timeouts, an allow-list of tools, validation of tool arguments, and human approval before anything irreversible such as sending email or paying.
Q08What is prompt injection, and how do you reduce the risk?SecurityAdvanced
Prompt injection is text inside retrieved documents, web pages or tool output that tries to give the model new instructions.
There is no complete fix, so limit the damage: treat retrieved content as data and mark it clearly, give tools the least privilege they need, require confirmation for sensitive actions, and check outputs before acting on them.
Also on its own page: Agentic AI & RAG interview questions