Agentic AI Engineering Program
Design, build, and deploy autonomous AI agents and complex agentic workflows using modern frameworks.
Program Overview
AI agents
Agentic workflows
Agent architectures
Tool use
Retrieval-Augmented Generation
Multi-agent systems
Agent orchestration
Observability
Practical implementation
What You'll Learn
- Understand Agentic AI concepts and terminology
- Design agent architectures
- Build AI agents using modern frameworks
- Work with tools and tool-calling patterns
- Build Agentic RAG systems
- Design multi-agent workflows
- Implement agent orchestration
- Understand agent observability
- Evaluate agent behavior and reliability
- Understand practical deployment considerations
Curriculum Modules
01 — Agentic AI Essentials
What is Agentic AI? AI agents vs traditional LLM applications, Agent capabilities, Agent loops, Tools and actions, Agentic workflows.
02 — Agentic Architectures & Design Patterns
Agent architecture, Planning, Reasoning, Tool use, Memory, Routing, Common agentic design patterns.
03 — LangChain & LCEL
LangChain fundamentals, Components, Chains, LCEL, Tool integration, Building agent workflows.
04 — LangGraph
Graph-based agent workflows, Nodes, Edges, State, Conditional routing, Stateful agent execution.
05 — Agentic RAG
RAG fundamentals, Retrieval, Context selection, Agent-driven retrieval, Tool-based retrieval, Agentic knowledge workflows.
06 — Phidata
Phidata fundamentals, Agent construction, Tools, Knowledge, Agent execution.
07 — Multi-Agent Systems
Multi-agent concepts, Agent roles, Collaboration, Delegation, Coordination, Multi-agent patterns.
08 — AutoGen
AutoGen fundamentals, Agent conversations, Multi-agent workflows, Tool integration, Practical agent orchestration.
09 — Agent Observability
Agent execution tracing, Logs, Metrics, Token usage, Cost awareness, Monitoring, Debugging agent workflows.
10 — No-Code / Low-Code Agentic AI Tools
No-code agent concepts, Low-code workflows, When to use visual tools, When to use engineering frameworks, Practical comparison of approaches.
Practical Application
Building an AI agent
Connecting agents to tools
Creating agent workflows
Building an Agentic RAG workflow
Designing a multi-agent workflow
Observing agent execution
Tracking token usage and approximate cost
Comparing framework-based and low-code approaches
Prerequisites
Basic Python programming knowledge
Understanding of APIs
Familiarity with software development concepts
Basic understanding of Generative AI / LLM concepts
Frequently Asked Questions
Who is this program designed for?
Experienced software engineers, tech leads, and IT professionals looking to build agentic systems.
Do I need Python experience?
Yes. Basic Python programming knowledge is highly recommended for building and connecting agents.
Do I need prior Generative AI knowledge?
Basic familiarity with LLM concepts is helpful, as this program focuses on the engineering architecture around LLMs.
Is this a hands-on engineering program?
Yes. Expect a 70% Technical / 30% Theory split, focusing on practical implementation and execution.
What frameworks are covered?
We cover LangChain, LangGraph, Phidata, AutoGen, and foundational concepts applicable across ecosystems.
How is Agentic AI different from a traditional LLM application?
Traditional applications are often single-turn or fixed-chain. Agents can reason, plan, use tools, and operate iteratively to solve complex problems.
Ready to take the next step?
Discuss your learning, career development or organizational technology capability needs.
Prefer WhatsApp? Message us on WhatsApp