IIT Delhi launches 6-month certificate programme in Agentic AI Systems

The Continuing Education Programme (CEP) of the Indian Institute of Technology Delhi has announced the first batch of its six-month Executive Certificate in Agentic AI Systems (Foundation to Deployment). The programme is designed to train professionals to build, coordinate and deploy autonomous AI systems for enterprise applications, with a focus on security, governance and responsible AI adoption.

The course moves beyond conventional generative AI, which primarily produces text, images and other content, to examine systems that can reason, plan, retrieve information, use external tools and coordinate actions to complete tasks. It will cover the development of individual AI agents as well as multi-agent systems that can work together on more complex workflows.

What will the course cover?

The curriculum is divided into eight core modules covering the foundations of agentic AI, prompt engineering and intelligent systems, autonomous agent design, enterprise knowledge systems, multi-agent orchestration, AI Trust, Risk and Security Management (AI TRiSM), application deployment and enterprise-scale operations.

Participants will learn about large language models (LLMs), Retrieval-Augmented Generation (RAG), and methods for connecting AI agents with external tools and data sources. The programme will also introduce frameworks and protocols such as Model Context Protocol (MCP), LangGraph, CrewAI and AutoGen, which are used to build and coordinate AI-powered workflows.

A dedicated module on AI TRiSM will examine issues that arise when organisations deploy autonomous systems, including model governance, explainability, security and regulatory compliance. The aim is to help participants assess the reliability of AI systems and understand the safeguards needed before deploying them in business settings.

Projects and practical learning

Practical assignments will form a key part of the six-month programme. Participants will progress from building individual AI assistants and knowledge-retrieval applications to developing workflows involving multiple agents.

The course will culminate in an end-to-end capstone project in which participants apply their learning to an agentic AI application while incorporating AI TRiSM principles. Learners will also work with relevant development frameworks, libraries and deployment tools, and evaluate the performance, security and operational reliability of their systems.

Story continues below this ad

The learning format will combine live faculty-led sessions with asynchronous learning resources. An optional campus immersion will also be available.

Who can apply?

The programme is intended for AI and data professionals, technology leaders, software developers, IT practitioners and science and engineering graduates seeking specialised training in agentic AI. Graduates from science, engineering and commerce disciplines are eligible to apply, while at least one year of professional experience is recommended.

Selection will involve a review of applications followed by a faculty interview. Participants will be assessed through mid-term and end-term multiple-choice examinations, assignments, quizzes and capstone projects. CEP, IIT Delhi will issue e-certificates to participants who meet the programme’s attendance and assessment requirements.

The programme comes as organisations explore the use of AI agents in areas such as customer service, information retrieval and business process automation. Unlike conventional AI applications that respond to individual prompts, agentic systems are designed to carry out sequences of actions towards a defined goal. Their deployment also raises questions around oversight, security and reliability, making these areas part of the course’s focus.