Course Outline
Structural Principles for AI System Design
- Layering, boundary definition, and separation of concerns
- Application of Ports and Adapters pattern to AI components
- Defining quality attribute scenarios for AI capabilities
- Utilizing architecture decision records for governance oversight
Modernizing Existing Applications
- Incremental modernization strategies versus complete rewrites
- Integrating AI services alongside legacy monolithic architectures
- Implementing Strangler Fig and anti-corruption layer patterns
- Establishing integration points for existing APIs and data stores
Architectural Patterns for LLM Integration
- Establishing the model gateway as an abstraction boundary
- Managing synchronous, asynchronous, and streaming communication
- Implementing fallback, degradation, and provider failover mechanisms
- Treating prompt and model configurations as version-controlled assets
Interfaces, APIs, and Data Exchange
- Defining structured output schemas and validation rules
- Enforcing idempotency, retry logic, and rate limiting
- Managing latency budgets and timeout orchestration
- Considering cost per request as an architectural constraint
End-to-End RAG Architecture
- Designing ingestion, chunking, and embedding pipelines
- Structuring index, retrieval, reranking, and generation stages
- Positioning retrieval services relative to application layers
- Analyzing trade-offs and failure modes at each stage
Vector Databases and Retrieval Strategies
- Evaluating managed versus self-hosted vector stores
- Implementing dense, sparse, and hybrid search methods
- Applying metadata filtering and tenant isolation controls
- Planning re-embedding strategies for model transitions
Retrieval Quality, Grounding, and Assessment
- Constructing evaluation sets from real-world query data
- Measuring retrieval and answer quality metrics
- Ensuring citation, grounding, and containment of hallucinations
- Incorporating feedback loops into index management
Agent System Architectures
- Defining the agent loop and tool invocation mechanisms
- Contrasting deterministic workflows with autonomous planners
- Identifying scenarios where agents are not the optimal solution
- Scoping agent responsibilities and state management
Multi-Agent Systems and Orchestration
- Designing supervisor and orchestrator topologies
- Establishing handoff protocols and message contracts
- Managing shared memory and context state
- Comparing frameworks based on architectural criteria
Service Communication and Tool Protocols
- Utilizing event-driven and queue-based coordination
- Exposing tools through standard protocols
- Implementing sagas, compensation, and long-running transactions
- Ensuring observability across service interactions
AI Agents in Development Workflows
- Integrating coding agents into delivery pipelines
- Applying spec-driven development and review gates
- Generating tests and executing automated quality checks
- Establishing guardrails to maintain architectural control
Governance and Software Quality Assurance
- Conducting design reviews for AI features
- Managing model and prompt changes systematically
- Integrating regression evaluation into the pipeline
- Defining ownership, policy, and approval pathways
Security, Privacy, and Data Governance
- Addressing prompt injection and defense in depth
- Managing secrets, access control, and least privilege
- Ensuring data residency, personal data handling, and retention
- Maintaining auditability and human-in-the-loop controls
Scalability, Cost, and Observability
- Tracing interactions across agent chains
- Monitoring token usage and cost telemetry
- Optimizing caching and latency performance
- Defining service levels and incident response for AI services
Capstone: Architecture for an AI-Powered Solution
- Developing context, component, and deployment views
- Designing retrieval and agent orchestration structures
- Formulating security, governance, and cost plans
- Executing peer review, critique, and migration roadmap creation
Requirements
- Experience in designing and maintaining production-grade software systems
- Proficiency in REST APIs and service integration
- Familiarity with relational databases and data modeling
- Basic exposure to LLM-based tools or APIs
Target Audience
- Software architects
- Technical leads and senior engineers
- Engineering managers responsible for architectural decisions
Testimonials (1)
That i gained a knowledge regarding streamlit library from python and for sure i'll try to use it to improve applications in my team which are made in R shiny