2025-cohort-2

Master Advanced Techniques for Building and Optimizing Agentic RAG Systems and Multi-Agent Workflows — Designed for Builders

Hamza Farooq

Agentic RAG Systems & Multi-Agent Architectures: Developers Edition

Google

Ucla

University of Minnesota

🧠 Masterclass in Agentic RAG &amp; Multi-Agent Deployment From Naive Bots to Production-Ready Agentic Systems Welcome to the AI builder’s dojo — a technically rigorous, unapologetically hands-on course designed for builders ready to go beyond plug-and-play wrappers and start designing agent systems that reason, route, and adapt. This is not a surface-level “course.” It’s a 10-week, live-led deep dive into autonomous systems: 7 instructor-led sessions · 7 interactive office hours · 1 epic Demo Day. No fluff. No wrappers. Just agents that work. 🧠 Course Breakdown – What You'll Learn 1. Agentic RAG with Routers — Why Naive RAG BreaksWe begin by deconstructing naive RAG — systems that fail under multi-turn, context-rich queries. You’ll build your own agentic retrieval system with intelligent routers, reflection, memory, and reasoning — capable of tool invocation, multi-agent coordination, and smart chunk selection.🔍 You’ll learn:-Stateless vs. stateful RAG-When cosine similarity fails-Designing context-aware routing logic-Reflection, ReAsk, and multi-hop search strategies 2. Hosting &amp; Quantizing LLMs — Local + RunpodProduction-ready agents can’t always rely on OpenAI. You’ll learn to quantize models (GPTQ, GGUF) for speed and cost-efficiency, and deploy them with Ollama locally and RunPod in the cloud, with tools like FastAPI and auto-scaling on demand. 🚀 You’ll learn:-LLM quantization strategies (4-bit, GGML, QLoRA)-On-device hosting via Ollama-Deployment via RunPod or serverless GCP-Streamed inference + latency benchmarking 3. Semantic Caching — Build It from ScratchWe’ll implement a semantic caching layer from scratch that recognizes similar queries, avoids unnecessary calls to the model, and improves performance over time using vector proximity and feedback loops.💡 You’ll build:Feedback loop to train your cacheCache hit/miss architectureSemantic distance functions + rerankingCost-saving and latency benchmarks 4. Knowledge Graphs from Scratch — Text-to-CypherGo beyond flat retrieval with structured reasoning using Knowledge Graphs. You’ll implement a graph-based memory layer with Cypher generation from natural language, and use DSPy to guide model outputs toward your schema.🌐 You’ll learn:Graph modeling for agent memoryExtracting entities + relations from unstructured textGenerating Cypher queries from promptsIntegrating Neo4j or Memgraph with RAG 5. ReAct Agents — Python &amp; No-Code with n8nWe’ll go deep into ReAct (Reason + Act) — one of the most powerful agent paradigms — and then rebuild it using both Python and no-code tools like n8n. Perfect for teams and workflows where technical + non-technical builders collaborate.🔧 You’ll build:Modular ReAct pipelines (tool use, planning, reflection)Human-in-the-loop agentsNo-code agents in n8n connected to APIs + databasesMulti-step workflows with visual orchestration 6. Bringing It All Together — ADK, MCP, A2A, and GuardrailsThe final sprint: we combine everything into a production system using Google’s ADK (Agent Development Kit), implement MCP (Modular Cognitive Planning), and create agent-to-agent (A2A) collaboration. You'll also implement industrial-grade guardrails and deploy securely with GCP integrations. 🛡️ You’ll ship:Multi-agent collaboration workflows-Safety guardrails using Llama Guard - Production deployment + monitoring- A capstone project solving a real-world enterprise task 🧩 Who This Is ForIf you’ve already built basic RAG tools or chatbots, and want to level up into true agent systems with autonomy, orchestration, and scale — this course is for you.-AI Engineers / LLM Builders-Technical Product Managers-Devs working on internal tools or AI copilots-Cloud / MLOps Engineers 🔧 What You’ll Get✅ 10 weeks of high-signal live instruction ✅ Weekly office hours + async support ✅ A final capstone project + demo day ✅ Real-world projects, not toy demos ✅ Guest lectures from AI builders at Google, Meta, OpenAI ✅ Early access to tools from Traversaal.ai ✅ Lifetime access to content + all future updates 🎓 PrerequisitesExperience building RAG or LLM-based toolsKnowledge of APIs, encoders/decoders, Python Basic understanding of cloud or serverless deployment👉 Need a ramp-up? Start with: Building LLM Applications: https://maven.com/boring-bot/ml-system-design 🎯 This Course Is For Builders Not marketers, not spectators — builders who want to deploy real AI.

The Agent Technical Course: Build and Deploy Production-Grade Gen AI Products

Machine Learning Engineer exploring different techniques to scale LLM solutions

Researcher, who would like to delve in to various aspects of open-source LLMs

Software Engineer, looking to learn how to integrate AI into their products

This course is for you if you are a:

What you’ll get out of this course

Understand and implement complex AI architectures, including enterprise-level RAG systems and agentic RAG strategies. You will also dive deep into the Mixture of Experts (MoE) technique and other model merging strategies to enhance the capabilities of your AI systems.

Advanced AI Architectures

From building semantic caches using GCP and Redis to deploying LLMs on serverless platforms like AWS Bedrock, you'll learn the practical skills to deploy and manage AI applications in real-world scenarios.&nbsp;

Practical Skills for Deployment

Acquire advanced techniques for fine-tuning LLMs, enabling you to adapt these models to specific tasks or domains and enhance their performance in targeted applications.

Fine-Tuning Expertise

Explore strategies for exploring and optimizing inference speeds, ensuring that your language models perform efficiently in real-time scenarios, a crucial skill for deploying responsive and scalable applications.

Efficient Inference Processing

Understand the importance of ethical AI development and learn to implement guardrails using tools like NeMo, Colang, and Llama Guard to ensure your AI systems align with responsible AI principles.

Knowledge of Responsible AI

Provide a brief description for each module as a way to sell the value of what students will be learning throughout the course.

First Module

Second Module

Third Module

Course syllabus

What people are saying

Meet your instructor

Saturdays

Work in teams to build solutions, this requires engagement with other team members

Weekly projects

Course schedule

This course builds on live workshops and hands-on projects

Active hands-on learning

You’ll be interacting with other learners through breakout rooms and project teams

Interactive and project-based

Join a community of like-minded people who want to learn and grow alongside you

Learn with a cohort of peers

Join <a href="https://boring-bot.kit.com/7406531a79" rel="noopener noreferrer" target="_blank">here</a> today

Course completed by

About this course

Get notified about the next cohort

Learn from live sessions