D24
Data & AIIntermediate10 weeks
Agentic AI
Learn to design, orchestrate, and ship autonomous AI agents that plan, use tools, and collaborate with each other to complete multi-step tasks.
What you'll learn
Building agents that reason, plan, and call tools using frameworks like LangChain and LlamaIndex
Giving agents memory and persistent state across sessions
Orchestrating multi-agent systems with supervisor/worker architectures
Evaluating, guarding, and deploying agents safely in production
Course details
Duration
10 weeks
Best for
Python developers who want to move beyond single-prompt apps and build autonomous, multi-agent AI systems
On completion
Verified certificate & placement assistance
Course Curriculum
A module-by-module breakdown of what you'll cover in Agentic AI.
01
LLM & API Foundations for Agents
Weeks 1–2- REST/async API clients with typed request and response schemas
- Rate limiting and retry logic
- Transformers, tokens, and context windows
- System/user/assistant roles and structured output
02
Prompt Engineering & Tool Use
Week 3- Few-shot and chain-of-thought prompting
- Designing function/tool schemas
- Tool selection, routing, and parallel calls
- Handling failed or malformed tool calls
03
Memory & State Management
Weeks 4–5- Short-term vs. long-term memory design
- Vector stores for semantic recall
- Conversation summarization
- Session and state persistence
04
Building Agents with Frameworks
Weeks 6–7- ReAct-style reasoning loops
- Agent abstractions in LangChain and LlamaIndex
- Planning vs. reactive agent design
- Agent tracing and debugging
05
Multi-Agent Orchestration
Week 8- Supervisor/worker and peer-to-peer architectures
- Task decomposition and planning
- Agent-to-agent communication and handoffs
- Building with LangGraph, CrewAI, and AutoGen
06
Evaluation, Guardrails & Deployment
Weeks 9–10- Building evaluation harnesses and benchmarks
- Hallucination and safety guardrails
- Human-in-the-loop approval gates
- Containerized deployment with observability
Tools & Technologies
Hands-on practice with the same tools used by working professionals.
ClaClaude / OpenAI Agent APIs
LanLangChain & LangGraph
LlaLlamaIndex
CreCrewAI / AutoGen
LanLangSmith / Langfuse
VecVector databases (Pinecone, Weaviate, pgvector)
FasFastAPI & Docker
Hands-on Projects
This is project-based learning — you'll build real, portfolio-ready work as you go, not just watch lectures.
Research assistant agent — a ReAct-style agent that plans multi-step research and synthesizes cited summaries
Support-ticket triage system — a two-agent pipeline that classifies and drafts responses, escalating edge cases to humans
Agentic codebase Q&A tool — an agent that iteratively rewrites and re-runs retrieval queries over a real codebase
Human-in-the-loop finance agent — an agent that proposes budget changes but requires explicit approval before acting
Deployed & monitored production agent — ship a containerized agent behind an API with tracing and a cost/latency dashboard
Every course includes a guided internship on top of your project work — so you graduate with real experience, not just a certificate.
Communication & Soft Skills
Built into every course, alongside the technical curriculum.
Communication Skills
Practice explaining technical work clearly to teammates, managers, and clients.
Teamwork & Collaboration
Work in small project teams using real workflows like stand-ups and code reviews.
Problem Solving
Build the habit of breaking down ambiguous problems into clear, solvable steps.
Time Management
Learn to plan, prioritize, and deliver project work against realistic deadlines.
Presentation Skills
Present your project work and results with confidence, as you would to a client.
Resume & Profile Building
Build a strong resume, LinkedIn profile, and project portfolio that recruiters notice.
Interview Preparation
Mock interviews and portfolio reviews to get you ready for real job applications.
Student Reviews
“Going from single-prompt scripts to a real multi-agent system with a supervisor and workers was the biggest jump in my skills this year.”
Karthik Iyer
Software Engineer
“The guardrails and human-in-the-loop module made me rethink my earlier agent projects entirely — safety design isn't an afterthought anymore.”
Meera Nair
AI Engineer
