IIT Delhi Launches Six-Month Executive Certificate in Agentic AI Systems, with Multi-Agent Orchestration and AI Governance in Focus

The Indian Institute of Technology (IIT) Delhi is opening admissions to the first batch of a six-month Executive Certificate in Agentic AI Systems (Foundation to Deployment), offered through its Continuing Education Programme (CEP). The course is aimed at working professionals who want to move past content-generating AI and learn how to build, coordinate and safely deploy autonomous AI agents inside enterprises.

From chatbots to agents that act

Where conventional generative AI tools answer a prompt with text or images, agentic systems are built to reason, plan, fetch information, call external tools and carry out a chain of actions towards a defined goal. The IIT Delhi programme covers both single agents and multi-agent systems that divide up and coordinate more complex workflows.

The curriculum is organised into eight core modules: 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.

Learners will work with large language models (LLMs) and Retrieval-Augmented Generation (RAG), and with ways of connecting agents to outside tools and data. The course also introduces widely used frameworks and protocols, including the Model Context Protocol (MCP), LangGraph, CrewAI and AutoGen.

Governance built into the syllabus

A dedicated AI TRiSM module looks at what changes when organisations hand tasks to autonomous systems: model governance, explainability, security and regulatory compliance. The intent is to help participants judge how reliable an AI system is and what safeguards it needs before it goes into a live business setting.

Hands-on work runs through the six months, with participants progressing from individual AI assistants and knowledge-retrieval apps to multi-agent workflows. The programme ends with an end-to-end capstone in which learners build an agentic AI application, apply AI TRiSM principles and evaluate its performance, security and operational reliability.

Format and eligibility

Teaching combines live, faculty-led sessions with self-paced material, and an optional campus immersion is available. The course is pitched at AI and data professionals, technology leaders, software developers, IT practitioners, and science and engineering graduates. Graduates in science, engineering and commerce are eligible, and at least one year of work experience is recommended.

Admission involves an application review followed by a faculty interview. Assessment is through mid-term and end-term multiple-choice examinations, assignments, quizzes and the capstone project, and CEP, IIT Delhi will issue e-certificates to those who meet attendance and assessment requirements.

Why it matters

Indian enterprises are beginning to pilot AI agents in customer service, information retrieval and business process automation, and the questions around oversight, security and reliability are growing with them. By putting deployment and governance on an equal footing with building agents, IIT Delhi’s programme adds to a fast-growing set of executive offerings from India’s leading institutes that aim to close the agentic-AI skills gap in the workforce.

Featured image: IIT Delhi Main Building. Photo by TheVyomanaut, via Wikimedia Commons, CC BY-SA 4.0.