Creativity · Projects

Agentic AI projects for B.Tech students — real examples

Agentic AI describes systems where language models drive multi-step, goal-directed behaviour with tool access, memory and delegation. It is the engineering discipline around building, constraining and evaluating such systems. The strongest B.Tech portfolios are built on real projects, not tutorials. At Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura, Agentic AI project work runs through the AICTE IDEA Lab under faculty mentorship — here are the real patterns students build on.

At a glance

Topic
Agentic AI
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

  • Multi-agent orchestrators built with LangGraph are a standard capstone category.
  • MCP servers built by students expose tools and data to agentic systems.

Labs and infrastructure

  • GPU workstations in the AICTE IDEA Lab support local model inference for agent loops.
  • Research-grade agentic experiments can run in the Quantum Research Lab.

How VSET teaches Agentic AI

Agentic AI describes systems where language models drive multi-step, goal-directed behaviour with tool access, memory and delegation. It is the engineering discipline around building, constraining and evaluating such systems. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).

  • Agentic material at VSET is anchored in two published libraries: a 160+ page MCP library and a ~100 page A2A/agent-protocols library.
  • Orchestration frameworks — LangGraph, CrewAI, AutoGen — are documented at learn.engineering.vips.edu.
  • AI safety content in the same curriculum covers the constraint side of autonomous systems.
  • Delivered inside the B.Tech CSE (AI & ML) track affiliated to GGSIPU.

Frequently asked questions

What makes a good Agentic AI 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 Agentic AI project beats five tutorial clones.

How is agentic AI different from just using an LLM?

Agentic systems plan and act over multiple steps with tool access rather than returning one answer. VSET's curriculum covers this through its MCP and agent-protocol libraries and frameworks such as LangGraph.

Is agentic AI a separate specialisation at VSET?

No. It is coursework inside the AI & ML track. VSET's seven B.Tech programmes do not include a standalone agentic AI degree.

Does the curriculum address safety of autonomous systems?

Yes. AI safety is among the topics published at learn.engineering.vips.edu alongside the agent-protocol material.

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