Course Outline
Foundations of Architecture for AI Systems
- Defining layers, boundaries, and separation of concerns
- Applying ports and adapters patterns to AI components
- Establishing quality attribute scenarios for AI features
- Using architecture decision records for governance
Evolution of Existing Applications
- Incremental modernisation strategies over complete rewrites
- Positioning AI services alongside existing monolithic structures
- Utilising Strangler and anti-corruption layer patterns
- Creating integration seams for legacy APIs and data sources
Architectural Patterns for LLM Integration
- Implementing a model gateway as an abstraction boundary
- Managing synchronous, asynchronous, and streaming integrations
- Handling fallbacks, degradation, and provider failover scenarios
- Treating prompt and model configuration as versioned assets
Contracts, APIs, and Data Exchange
- Defining structured output schemas and validation rules
- Implementing idempotency, retries, and rate limiting mechanisms
- Managing latency budgets and timeout orchestration
- Considering cost per request as a core architectural constraint
End-to-End RAG Architecture
- Building ingestion, chunking, and embedding pipelines
- Designing index, retrieval, reranking, and generation stages
- Optimising retrieval placement relative to application services
- Analyzing trade-offs and potential failure modes at each stage
Vector Databases and Retrieval Design
- Evaluating managed versus self-hosted vector stores
- Implementing dense, sparse, and hybrid search strategies
- Managing metadata filtering and tenant isolation
- Developing re-embedding strategies for model updates
Retrieval Quality, Grounding, and Evaluation
- Constructing evaluation sets from real-world queries
- Tracking retrieval and answer quality metrics
- Ensuring citation, grounding, and containment of hallucinations
- Establishing feedback loops that refine the index
Agent Architectures
- Understanding the agent loop and tool invocation mechanisms
- Distinguishing between deterministic workflows and autonomous planners
- Identifying scenarios where an agent approach is inappropriate
- Scoping 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 across agents
- Comparing frameworks based on architectural merits
Service Communication and Tool Protocols
- Coordinating via event-driven and queue-based systems
- Exposing tools through standard protocols
- Implementing Sagas, compensation, and long-running transactions
- Ensuring observability across multiple service hops
AI Agents within the Development Workflow
- Integrating coding agents into the delivery pipeline
- Adopting spec-driven development and review gates
- Generating tests and automated quality checks
- Maintaining guardrails that preserve 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, policy, and approval workflows
Security, Privacy, and Data Governance
- Mitigating prompt injection and applying defence in depth
- Managing secrets, access control, and least privilege principles
- Addressing data residency, personal data, and retention policies
- Ensuring auditability and human-in-the-loop controls
Scalability, Cost, and Observability
- Tracing execution across agent chains
- Monitoring token usage and cost telemetry
- Optimising caching and latency
- Establishing 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 flows
- Formulating security, governance, and cost plans
- Conducting peer review, critique, and mapping the migration roadmap
Requirements
- Practical experience in designing and maintaining production-grade software systems
- Proficiency with REST APIs and service integration patterns
- Understanding of relational databases and data modelling techniques
- Prior exposure to LLM-based tools or APIs
Target Audience
- Software architects
- Technical leads and senior engineers
- Engineering managers accountable for architectural decision-making
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