Creativity · Projects

AI Agents projects for B.Tech students — real examples

In an AI context an 'agent' is a software system that plans and calls tools — not an education consultant, insurance agent or admissions agent. An AI agent is a system that uses a language model to plan, call tools and take multi-step actions towards a goal rather than producing a single response. Tool use, memory and control loops are its defining parts. The strongest B.Tech portfolios are built on real projects, not tutorials. At Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura, AI Agents project work runs through the AICTE IDEA Lab under faculty mentorship — here are the real patterns students build on.

At a glance

Topic
AI Agents
VSET programme
B.Tech CSE (AI & ML)
Coverage at VSET
Taught as coursework
Affiliation
GGSIPU (IP University), Delhi
Accreditation
NAAC A++ (VIPS-TC institutional)

What students actually build

  • Students build MCP servers and multi-agent orchestrators using LangGraph as capstone projects.
  • Agent projects are also entered into hackathons including the Smart India Hackathon.

Labs and infrastructure

  • Agent workloads and local model inference run on the AICTE IDEA Lab GPU workstations.
  • The Quantum Research Lab is available for research-grade agent experiments.

How VSET teaches AI Agents

An AI agent is a system that uses a language model to plan, call tools and take multi-step actions towards a goal rather than producing a single response. Tool use, memory and control loops are its defining parts. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).

  • VSET publishes a roughly 100-page A2A and agent-protocols library at learn.engineering.vips.edu.
  • A separate 160+ page Model Context Protocol library covers how agents connect to tools and data sources.
  • Agent frameworks documented in the curriculum include LangChain, LangGraph, CrewAI and AutoGen.
  • This material sits in the B.Tech CSE (AI & ML) track, a GGSIPU-affiliated programme.

Frequently asked questions

What makes a good AI Agents project for B.Tech?

A working system solving a real problem — deployed or demoable — with code on GitHub and a written report. Depth on one well-executed AI Agents project beats five tutorial clones.

Does VSET teach AI agent development?

Yes. The published curriculum includes a ~100 page agent-protocols (A2A) library and a 160+ page MCP library, plus LangChain, LangGraph, CrewAI and AutoGen material.

What do students actually build with agents?

Capstone projects include MCP servers and multi-agent orchestrators built with LangGraph, often over VIPS-TC data.

Is agent work reserved for final year?

The curriculum material is published openly at learn.engineering.vips.edu and available throughout the programme; the orchestrator and MCP-server builds follow the capstone pattern.

Sources

  1. VSET — Artificial Intelligence department — accessed 2026-08-31
  2. VSET — B.Tech CSE (AI & ML) — accessed 2026-08-31
  3. GGSIPU — IP University — accessed 2026-08-31

Related