GenAI & Agentic AI Workshop
Hands-on projects

Projects

Six small projects, one per lab. Each one adds a piece, and together they become a campus helpdesk agent you can put on your GitHub and resume.

The campus helpdesk agent in the centre. A student asks a question. The agent uses memory (Project 2), searches the college FAQ with RAG (Project 3), calls a timetable tool over MCP (Project 4), follows guardrails (Session 5), and can be deployed as an API (Session 9).
How the projects fit together. Source: helpdesk-architecture.drawio (open in draw.io to edit).
#ProjectSessionLevelStatus
1Prompt Lab2. Prompt engineeringBeginnerStarter ready
2Chatbot with memory3. LLM APIsBeginnerStarter ready
3Chat with the syllabus (RAG)4. RAGIntermediateStarter ready
4Timetable agent + MCP server7. Tool calling & MCPIntermediateComing soon
5Research team (multi-agent)8. Agent frameworksIntermediateComing soon
6Campus helpdesk agent10. Mini projectCapstoneComing soon
What you need A Google account for Google Colab and a free Gemini API key from Google AI Studio (or a Groq key). No installs, no credit card.

Day 1: Generative AI

Project 1 · Prompt Lab

Session 2Beginner20 minStarter ready

Take three everyday tasks, write a weak and a strong prompt for each, and compare the answers. Learn what actually makes a prompt good.

You will build:

Stretch: test your complaint router on 20 real complaints and count how many it gets right. That's your first evaluation.

Project 2 · Chatbot with memory

Session 3Beginner25 minStarter ready

Call an LLM from Python and build "CampusBuddy", a chatbot that remembers the conversation. You'll see that "memory" is just re-sending the chat history each time.

Stretch: keep only the last 6 messages, retry on rate limits, or switch the bot to Groq.

Project 3 · Chat with the syllabus (RAG)

Session 4Intermediate45 minStarter ready

Make the chatbot answer from college documents, with citations, instead of guessing. The starter uses a sample FAQ for a fictional college; then you swap in your own college's PDF.

Stretch: upload your own college PDF, tune chunk size, k and the minimum score, or add memory from Project 2.

Day 2: Agentic AI

Project 4 · Timetable agent + MCP server

Session 7Intermediate45 minComing soon

Give the LLM a tool. The agent decides when to call get_exam_date(subject) or a weather API, reads the result, and answers.

Stretch: add a second tool (library hours) and see the agent pick the right one.

Project 5 · Research team (multi-agent)

Session 8Intermediate45 minComing soon

Two agents working together: a researcher collects facts on a topic and a writer turns them into a short report.

Stretch: add a third "reviewer" agent that checks the report for mistakes.

Capstone

Project 6 · Campus helpdesk agent

Session 10Capstone60 minComing soon

Put it all together. A student asks "When is my DBMS exam, and is the library open on Sunday?" and the agent answers using everything you built.

PieceComes from
System prompt with role and rulesProject 1
Conversation memoryProject 2
Answers from the college FAQ, with sourcesProject 3
Timetable tool over MCPProject 4
Guardrails: "I don't know", no personal dataSession 5
Deployed as an API (stretch)Session 9
Make it portfolio-ready Push it to GitHub with a README that has a screenshot, a diagram, how to run it, and 5 example questions it answers well and 2 it refuses correctly. Deploy it and add the link to your resume.

More project ideas for your portfolio

IdeaUses
Resume reviewer that scores a resume against a job descriptionPrompting, JSON output
Previous-year question paper bot: "show me all DBMS questions on normalisation"RAG
Kannada / Hindi / Tamil FAQ bot for the college officeRAG, multilingual models
Interview practice agent that asks questions and gives feedbackSystem prompts, memory
Expense tracker that reads bill photos and fills a Google SheetVision model, tools
GitHub repo explainer: "how does this project work?"RAG over code, agents