Course syllabus
Generative AI with Agentic AI
Weekend batch to become an LLM / AI Agent Engineer — tools, memory, multi-agent systems, and production-safe agents
Relaunch offer — first 2 batches only
Weekend-only cohort (core 8 weekends / 9 modules; stretch to 10 weekends). 100% online — live, interactive, and flexible. Join from home or anywhere. Designed for working professionals and aspiring Agentic AI engineers.
Who it’s for: Software, cloud, RPA, PM, data, finance/ops/HR professionals who want to build LLM agents with tools, APIs, and memory.
After you pay
What enrollment unlocks
Payment is processed on Feednet Solutions. Approved students get the learning home, recordings, and assessments there.
- Access to everyday class recording sessions
- Daily assessments + module-wise and weekly assessments
- Saturday assignments that raise your score
- Monthly grand test / monthly offline or online interview
- Learning-home (LMS) dashboard after enrollment
- Resume, portfolio & mock-interview support on the paid track
Curriculum
Modules
-
Module 1 — Core Python (must master)
- Variables and data types; operators (arithmetic, logical, comparison, assignment)
- Conditional statements (if / elif / else); loops (for / while)
- Functions (regular & lambda); exception handling (try / except / finally)
- File handling; data structures (list, tuple, set, dictionary)
- Modules and packages (import / from … import)
- Hands-on: calculator, word counter, file analyzer mini-projects
-
Module 2 — Generative AI foundations
- What is Generative AI vs traditional AI
- Transformer architecture overview; tokenization & embeddings
- Prompt engineering (basic → advanced): few-shot, zero-shot, chain-of-thought
- LLMs: OpenAI (GPT), Gemini, Claude, LLaMA, Mistral
- How LLMs generate text — sampling, temperature, top-p
- Fine-tuning vs Retrieval-Augmented Generation (RAG)
- Model APIs & SDKs — openai, google-generativeai, anthropic
- Text cleaning & chunking; vector embeddings (sentence-transformers, OpenAIEmbeddings)
- Vector stores — FAISS, ChromaDB, Pinecone; knowledge retrieval & context injection
- LangChain basics — chains, tools, agents, memory; PromptTemplates & OutputParsers
- Tool calling, API integration, function calling with LLMs
- Hands-on: Generative AI Q&A assistant with LangChain + OpenAI API
-
Module 3 — Agentic AI foundations
- What is Agentic AI? Why now?
- Reactive vs proactive agents; agent vs chatbot vs tool
- Real-world agent use cases across industries
- Framework overview: Phidata, LangChain, AutoGen, CrewAI
- Hands-on: minimal agent + tool + goal execution
-
Module 4 — Intelligent agent architecture & planning
- Reflex, model-based, and goal-based agent architectures
- ReAct and CoT (chain of thought) execution models
- Agent planning, task decomposition & contextual reasoning
- Multi-step reasoning via Phidata + LangChain
- Hands-on: agent that plans and executes multi-step tasks
-
Module 5 — LangChain, LangGraph & CrewAI deep dive
- LangChain and LangGraph agents, memory, retrievers, vector stores
- Chains vs agents vs tools (LangChain distinction)
- Multi-agent crew workflows with CrewAI
- Crew roles, goals, and delegation strategies
- Hands-on: multi-role agent team for content generation or automation
-
Module 6 — Prompt engineering, function calling & tool mastery
- Structured prompting techniques
- Function calling with OpenAI, Anthropic, Gemini
- Integrating tools (search, math, APIs, file access)
- Tool orchestration inside agents
- Hands-on: dynamic function agent that solves complex tasks with tools
-
Module 7 — Phidata + real-world deployment agents
- Full-stack agent setup with Phidata
- Tool + UI + memory + agents in one place
- RAG agents with vector DBs
- API integration with Cloud, Jira, CRM, DB
- Hands-on: AI assistant for ticket triage / cloud monitoring / PM bot
-
Module 8 — Observability, guardrails & human-in-the-loop
- Agent monitoring, logs, debugging (LangSmith, internal logging)
- Ethical AI, prompt injection & defense
- HITL design + approval workflows
- Model Context Protocol (MCP)
- Evaluating agent quality (cost, accuracy, time)
- Hands-on: deploy an enterprise-safe agent with HITL
-
Module 9 — Capstone project + career transition
- Capstone: choose your domain and build an agent system
- Examples: AI PM assistant, RPA supervisor bot, cloud monitor, compliance agent, coding assistant
- Streamlit / FastAPI-based deployment
- Token cost optimization, caching, scaling
- Resume, GitHub & portfolio boosting
- Live presentation + feedback + deployment guidance
- Stretch weekends 9–10 (batch-dependent): advanced multi-agent patterns & interview labs