Course Outline
Foundational Architecture for AI Systems
- Layers, boundaries, and separation of concerns
- Applying ports and adapters to AI components
- Defining quality attribute scenarios for AI features
- Using architecture decision records for governance
Evolving Existing Applications
- Incremental modernisation rather than full rewrites
- Positioning AI services alongside existing monoliths
- Utilising strangler and anti-corruption layer patterns
- Creating integration seams for existing APIs and data
LLM Integration Architectural Patterns
- Implementing a model gateway as an abstraction boundary
- Handling synchronous, asynchronous, and streaming integrations
- Managing fallback, degradation, and provider failover
- Treating prompt and model configuration as versioned assets
Contracts, APIs, and Data Exchange
- Structured output schemas and validation processes
- Ensuring idempotency, retries, and rate limiting
- Managing latency budgets and timeout orchestration
- Treating cost per request as an architectural constraint
End-to-End RAG Architecture
- Ingestion, chunking, and embedding pipelines
- Stages for indexing, retrieval, reranking, and generation
- Positioning retrieval relative to application services
- Analyse trade-offs and failure modes at each stage
Vector Databases and Retrieval Design
- Comparing managed versus self-hosted vector stores
- Dense, sparse, and hybrid search strategies
- Metadata filtering and tenant isolation
- Re-embedding strategies when models evolve
Retrieval Quality, Grounding, and Evaluation
- Building evaluation sets from real-world queries
- Measuring retrieval and answer quality
- Citation, grounding, and containing hallucinations
- Implementing feedback loops into the index
Agent Architectures
- The agent loop and tool invocation mechanisms
- Deterministic workflows versus autonomous planners
- Identifying cases where an agent is inappropriate
- Scoping agent responsibilities and state management
Multi-Agent Systems and Orchestration
- Supervisor and orchestrator topologies
- Handoff protocols and message contracts
- Shared memory and context management
- Comparing frameworks on architectural grounds
Service Communication and Tool Protocols
- Event-driven and queue-based coordination
- Exposing tools through standard protocols
- Sagas, compensation, and long-running transactions
- O bservability across service hops
AI Agents in Development Workflows
- Integrating coding agents into the delivery pipeline
- Spec-driven development and review gates
- Test generation and automated quality checks
- Establishing guardrails to preserve architectural control
Governance and Software Quality
- Conducting design reviews for AI features
- Managing model and prompt changes
- Including regression evaluation as a pipeline stage
- Defining ownership, policy, and approval paths
Security, Privacy, and Data Governance
- Addressing prompt injection and defence in depth
- Managing secrets, access control, and least privilege
- Ensuring data residency, personal data protection, and retention
- Maintaining auditability and human-in-the-loop controls
Scalability, Cost, and Observability
- Tracing across agent chains
- Monitoring token and cost telemetry
- Optimising caching and latency
- 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
- Formulating security, governance, and cost plans
- Peer review, critique, and migration roadmap
Requirements
- Experience in designing and maintaining production-level software systems
- Practical knowledge of REST APIs and service integration
- Familiarity with relational databases and data modelling
- 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