System Design & Architecture
Designing scalable Gen AI systems: RAG pipelines, multi-model architectures, latency optimization, and production system design.
0
Easy Concepts
3
Medium Concepts
10
Hard Concepts
Medium Concepts (3)
Explain the deployment options for Google ADK agents (Vertex AI, Cloud Run, GKE, Docker).
google-adkdeploymentvertex-aicloud-rungke
Explain the tool execution flow and Human-in-the-Loop (HITL) pattern in Google ADK.
google-adktoolshitlhuman-in-the-loopconfirmation
How do LLMs set their maximum context window? Explain the role of architecture, training, and API configuration.
gen-aicontext-windowllmarchitecturetoken-limits
Hard Concepts (10)
Design a RAG system for a customer support chatbot. Walk through your architecture.
gen-aisystem-designrag
View Details →Code
How would you handle out-of-scope queries in the RAG system?
gen-aisystem-designrag
View Details →Code
How would you evaluate if your RAG system is better than fine-tuning?
gen-aisystem-designragfine-tuning
View Details →Code
Provide me complete architecture of how a Chat LLM works in detail
system-designarchitecturetransformerattentionrag
View Details →Code
Explain the runtime architecture of Google ADK (Runner, Session, Events, InvocationContext) with flow diagrams.
google-adkruntimerunnersessionevents
How to design a multi-agent orchestration system using Google ADK's workflow agents (Sequential, Parallel, Loop)?
google-adkorchestrationworkflowsequentialparallel
How to build a production-grade Chat Application using Google ADK? Explain the complete flow with orchestration agents, sub-agents, guardrails, and security measures.
google-adkchat-applicationorchestrationmulti-agentsequential-agent
How to build a production-grade RAG Application using Google ADK? Explain the complete flow with document ingestion, multi-source retrieval, hallucination guards, and security measures.
google-adkragretrieval-augmented-generationorchestrationmulti-agent