Course Outline
Foundational Architecture for AI Systems
- Defining layers, boundaries, and separation of concerns
- Applying ports and adapters patterns to AI components
- Quality attribute scenarios specific to AI features
- Using Architecture Decision Records (ADRs) for governance
Modernizing Existing Applications
- Incremental modernization strategies over full rewrites
- Positioning AI services alongside legacy monoliths
- Utilizing Strangler Fig and Anti-Corruption Layer patterns
- Creating integration points for existing APIs and data sources
LLM Integration Architecture Patterns
- Model gateways as abstraction boundaries
- Handling synchronous, asynchronous, and streaming integrations
- Implementing fallback, degradation, and provider failover strategies
- Treating prompt and model configurations as versioned assets
Contracts, APIs, and Data Exchange
- Defining structured output schemas and validation rules
- Managing idempotency, retries, and rate limiting
- Allocating latency budgets and orchestrating timeouts
- Treating cost per request as a key architectural constraint
End-to-End RAG Architecture
- Building ingestion, chunking, and embedding pipelines
- Designing index, retrieval, reranking, and generation stages
- Positioning retrieval relative to application services
- Analyzing trade-offs and failure modes at each stage
Vector Databases and Retrieval Design
- Comparing managed versus self-hosted vector stores
- Implementing dense, sparse, and hybrid search techniques
- Applying metadata filtering and tenant isolation
- Developing re-embedding strategies for model changes
Retrieval Quality, Grounding, and Evaluation
- Constructing evaluation sets from real-world queries
- Measuring retrieval and answer quality metrics
- Managing citations, grounding, and hallucination containment
- Establishing feedback loops to refine the index
Agent Architectures
- Understanding the agent loop and tool invocation
- Contrasting deterministic workflows with autonomous planners
- Identifying scenarios where agents are inappropriate
- Defining agent responsibilities and state management
Multi-Agent Systems and Orchestration
- Designing supervisor and orchestrator topologies
- Defining handoff protocols and message contracts
- Managing shared memory and context
- Comparing frameworks based on architectural merits
Service Communication and Tool Protocols
- Coordinate via event-driven and queue-based mechanisms
- Exposing tools through standard protocols
- Implementing sagas, compensation, and long-running transactions
- Ensuring observability across service hops
AI Agents in the Development Workflow
- Integrating coding agents into delivery pipelines
- Adopting spec-driven development and review gates
- Leveraging test generation and automated quality checks
- Establishing guardrails to maintain architectural control
Governance and Software Quality
- Conducting design reviews for AI features
- Managing changes to models and prompts
- Including regression evaluation as a pipeline stage
- Defining ownership, policies, and approval workflows
Security, Privacy, and Data Governance
- Defending against prompt injection with defense in depth
- Managing secrets, access control, and least privilege
- Handling data residency, personal data, and retention policies
- Ensuring auditability and human-in-the-loop controls
Scalability, Cost, and Observability
- Tracing operations across agent chains
- Monitoring token usage and cost telemetry
- Optimizing caching and latency
- Defining service levels and incident response for AI services
Capstone: Architecture for an AI-Powered Solution
- Mapping context, component, and deployment views
- Designing retrieval and agent orchestration strategies
- Planning for security, governance, and cost management
- Conducting peer reviews, critiques, and migration roadmaps
Requirements
- Proven experience in designing and maintaining production-grade software systems
- Proficiency in REST APIs and service integration patterns
- Understanding of relational databases and data modeling
- Basic familiarity with LLM-based tools or APIs
Target Audience
- Software Architects
- Technical Leads and Senior Engineers
- Engineering Managers overseeing 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