Creativity · Projects

AutoGen projects for B.Tech students — real examples

AutoGen is an open-source framework for building conversational multi-agent applications where agents exchange messages, call tools and involve humans in the loop. It centres on agent conversation patterns. The strongest B.Tech portfolios are built on real projects, not tutorials. At Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura, AutoGen project work runs through the AICTE IDEA Lab under faculty mentorship — here are the real patterns students build on.

At a glance

Topic
AutoGen
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

  • Conversational multi-agent patterns feed into the orchestrator capstones students build.
  • Agent builds are entered into hackathons including the Smart India Hackathon.

Labs and infrastructure

  • Agent conversation loops against local models run on the AICTE IDEA Lab GPU workstations.

How VSET teaches AutoGen

AutoGen is an open-source framework for building conversational multi-agent applications where agents exchange messages, call tools and involve humans in the loop. It centres on agent conversation patterns. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).

  • AutoGen is one of the agent frameworks documented in the VSET AI curriculum at learn.engineering.vips.edu.
  • It is taught alongside LangGraph and CrewAI for comparison of orchestration models.
  • The ~100 page A2A/agent-protocols library gives the messaging background AutoGen relies on.
  • Delivered inside the GGSIPU-affiliated B.Tech CSE (AI & ML) track at VSET.

Frequently asked questions

What makes a good AutoGen 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 AutoGen project beats five tutorial clones.

Is AutoGen covered at VSET?

Yes — it appears in the published AI curriculum at learn.engineering.vips.edu alongside LangChain, LangGraph, CrewAI and LlamaIndex.

Which framework is used for the capstone orchestrators?

The documented capstone pattern names LangGraph for multi-agent orchestrators; AutoGen is covered as another conversational multi-agent approach.

Why teach several agent frameworks?

Because the underlying protocols matter more than any one library — VSET pairs the frameworks with a 160+ page MCP library and a ~100 page agent-protocols library.

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