Course Outline
Architectural Foundations 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.
- Utilizing architecture decision records as governance tools.
Evolving Existing Applications
- Prioritizing incremental modernization over full rewrites.
- Integrating AI services alongside existing monolithic structures.
- Employing Strangler Fig and Anti-Corruption Layer patterns.
- Creating integration points for legacy APIs and data sources.
Architectural Patterns for LLM Integration
- Implementing model gateways as abstraction boundaries.
- Handling synchronous, asynchronous, and streaming integration models.
- Designing fallback mechanisms, degradation strategies, and provider failover.
- Managing prompts and model configurations as version-controlled assets.
Contracts, APIs, and Data Exchange
- Defining structured output schemas and validation rules.
- Managing idempotency, retries, and rate limiting.
- Setting 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.
- Structuring index, retrieval, reranking, and generation stages.
- Positioning retrieval logic 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 techniques.
- Applying metadata filtering and ensuring tenant isolation.
- Planning re-embedding strategies for model updates.
Retrieval Quality, Grounding, and Evaluation
- Constructing evaluation sets from real-world query data.
- Measuring retrieval accuracy and answer quality.
- Ensuring citation integrity, grounding, and hallucination containment.
- Implementing feedback loops to optimize the index.
Agent Architectures
- Understanding the agent loop and tool invocation mechanisms.
- Comparing deterministic workflows with autonomous planners.
- Identifying scenarios where agents are not the appropriate solution.
- Defining the scope of 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 across agents.
- Comparing frameworks based on architectural merits.
Service Communication and Tool Protocols
- Utilizing event-driven and queue-based coordination.
- Exposing tools via standard industry protocols.
- Implementing Sagas, compensation, and long-running transaction handling.
- Ensuring observability across multiple service hops.
AI Agents in Development Workflows
- Integrating coding agents within the delivery pipeline.
- Adopting spec-driven development with review gates.
- Leveraging test generation and automated quality checks.
- Establishing guardrails to maintain architectural integrity.
Governance and Software Quality
- Conducting design reviews for AI-specific features.
- Managing changes to models and prompts.
- Incorporating regression evaluation as a standard pipeline stage.
- Defining ownership, policy, and approval workflows.
Security, Privacy, and Data Governance
- Mitigating prompt injection through defense-in-depth strategies.
- Managing secrets, access control, and least-privilege principles.
- Handling data residency, personal data, and retention policies.
- Ensuring auditability and human-in-the-loop oversight.
Scalability, Cost, and Observability
- Tracing processes across agent chains.
- Monitoring token usage and cost telemetry.
- Optimizing caching and latency performance.
- Defining service levels and incident response for AI services.
Capstone: Architecting an AI-Powered Solution
- Developing context, component, and deployment views.
- Designing retrieval and agent orchestration flows.
- Formulating security, governance, and cost management plans.
- Conducting peer review, critique, and roadmap migration planning.
Requirements
- Proven experience in designing and sustaining production-grade software systems.
- Practical understanding of REST APIs and service integration patterns.
- Familiarity with relational databases and data modeling concepts.
- Basic exposure to LLM-based tools or APIs.
Target Audience
- Software Architects
- Technical Leads and Senior Engineers
- Engineering Managers with responsibility 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