Building Agentic AI Systems with Small Language Models

Introduction

3-hour hands-on workshop equips participants to design, build, and optimize real-world AI systems powered by Small Language Models (SLMs). Unlike traditional LLM-heavy approaches, this workshop focuses on cost-efficient, production-aware architectures that run entirely within Google Colab’s free tier—making advanced AI engineering accessible without expensive compute infrastructure.

Participants will progress through building toward a complete multi-agent RAG-enabled AI system that solves a real-world problem. Every module includes end-to-end hands-on demos with pre-configured notebooks that participants take home after the session.

Target Audience

• AI/ML engineers and data scientists seeking cost-efficient model deployment strategies

• GenAI practitioners evaluating SLMs as alternatives or complements to large LLMs

• Engineers building production LLM/SLM applications under compute or budget constraints

Prerequisites

• Proficiency in Python (intermediate level; ability to read and write functions, classes, and scripts)

• Foundational familiarity with machine learning concepts or prior exposure to LLMs/NLP is helpful but not required

• A Google account for Colab and Drive access

Content Provided

• Google Colab notebooks with complete, runnable code

• Curated small datasets for inference, fine-tuning, and RAG experiments

• Reference slides covering theory, architecture diagrams, and design pattern summaries

Infrastructure

• Google Colab (Free Tier) — CPU-first design; GPU optional for fine-tuning acceleration

• Google Drive for notebook persistence and model checkpoint storage

• No paid cloud resources required; all demos run within free-tier constraints

Speakers:

Nitin Agarwal, Sanathraj Narayan

By the end of this workshop, participants will be able to:

• Deploy and run inference with SLMs (like Phi-3 Mini, Gemma 2B) within Google Colab free-tier limits

• Apply quantization techniques and parameter-efficient fine-tuning with QLoRA for domain-specific tasks

• Architect an end-to-end Agentic RAG system combining retrieval, reasoning, and generation under constrained compute

• Evaluation of AI system using SLM-as-a-Judge and observability