AI Engineering Program · Part 2 of 3

AI Engineering 2: Agentic AI & MCP – Build Autonomous Agents

Design AI agents that plan, use tools and collaborate, using the OpenAI Agents SDK, CrewAI, LangGraph, AutoGen and Model Context Protocol.

⏱ 2 months◆ Intermediate● Live + hands-on★ Internship eligible
Mentored by Amit Singh, CTO, Incred · Ex-LangChain, NVIDIA, IBM

What you'll learn

  • Understand agent loops, tools and when to use workflows vs agents
  • Apply proven patterns: chaining, routing, orchestrator-workers, evaluator-optimizer
  • Build agents with the OpenAI Agents SDK: handoffs, guardrails, tracing
  • Create role-based agent teams with CrewAI
  • Build stateful, human-in-the-loop agents with LangGraph
  • Run multi-agent conversations with AutoGen
  • Build and connect your own MCP servers
  • Ship a multi-agent capstone end-to-end

Curriculum

6 modules · 20 topics · hands-on labs in every module
Week 1: Foundations of Agents4 topics
  • What makes a system 'agentic'
  • Agent loop, tools and memory
  • Workflow patterns vs autonomous agents
  • Project: career assistant agent for your own profile
Week 2: OpenAI Agents SDK3 topics
  • Agents, tools and handoffs
  • Guardrails and tracing
  • Project: deep-research agent
Week 3: CrewAI3 topics
  • Crews, agents, tasks and roles
  • Structured outputs and memory
  • Project: AI engineering team that writes and tests code
Week 4: LangGraph3 topics
  • Graphs, state and checkpointing
  • Human-in-the-loop and long-term memory
  • Project: browser-using sidekick agent
Week 5: AutoGen3 topics
  • Multi-agent conversations
  • Agents that create other agents
  • Distributed agent runtimes
Week 6: Model Context Protocol (MCP)4 topics
  • MCP hosts, clients and servers
  • Building your own MCP server (Python & TypeScript)
  • Connecting agents to real tools and data
  • Capstone: multi-agent trading-floor simulation

Requirements

About this program

Agents are where AI moves from answering questions to doing work. This is Part 2 of the AI Engineering program, taught by an engineer who helped build agent frameworks at LangChain.

You will compare the major frameworks hands-on and learn when to reach for each.

After this program you can join the 6-month internship and take part in the ownership model: build an Incred vertical and earn a share, sell your product locally, or pitch your own idea for funding.


Your mentor

Amit Singh

Amit Singh

CTO, Incred Applications Pvt Ltd · IIT Delhi alumnus

Leads the global engineering team of incred.golf across Germany, London, Croatia, India and Denver. Ex-lead at LangChain; previously with NVIDIA and IBM.