Course Outline
Architectural Foundations 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 modernization versus complete rewrites.
- Positioning AI services alongside existing monoliths.
- Utilizing strangler and anti-corruption layer patterns.
- Creating integration points for existing APIs and data.
LLM Integration Architectural Patterns
- Model gateways as abstraction boundaries.
- Synchronous, asynchronous, and streaming integration methods.
- Implementing fallback, degradation, and provider failover strategies.
- Managing prompts and model configurations as versioned assets.
Contracts, APIs, and Data Exchange
- Structured output schemas and validation techniques.
- Idempotency, retries, and rate limiting mechanisms.
- Latency budgets and timeout orchestration.
- Treating cost per request as an architectural constraint.
End-to-End RAG Architecture
- Ingestion, chunking, and embedding pipelines.
- Stages of indexing, retrieval, reranking, and generation.
- Positioning retrieval relative to application services.
- Analyzing trade-offs and failure modes at each stage.
Vector Databases and Retrieval Design
- Managed versus self-hosted vector stores.
- Dense, sparse, and hybrid search techniques.
- Metadata filtering and tenant isolation strategies.
- Re-embedding strategies when models are updated.
Retrieval Quality, Grounding, and Evaluation
- Building evaluation sets from real-world queries.
- Metrics for retrieval and answer quality.
- Citation, grounding, and containing hallucinations.
- Implementing feedback loops to improve the index.
Agent Architectures
- The agent loop and tool invocation processes.
- Deterministic workflows versus autonomous planners.
- Identifying scenarios where agents are not the right solution.
- 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.
- Framework comparisons based on architectural merits.
Service Communication and Tool Protocols
- Event-driven and queue-based coordination.
- Exposing tools via standard protocols.
- Sagas, compensation, and long-running transactions.
- Observability 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 maintain architectural control.
Governance and Software Quality
- Design reviews for AI features.
- Managing changes to models and prompts.
- Incorporating regression evaluation as a pipeline stage.
- Defining ownership, policy, and approval paths.
Security, Privacy, and Data Governance
- Defending against prompt injection and adopting defense in depth.
- Managing secrets, access control, and least privilege.
- Addressing data residency, personal data, and retention policies.
- Ensuring auditability and implementing human-in-the-loop controls.
Scalability, Cost, and Observability
- Tracing across agent chains.
- Monitoring token usage and cost telemetry.
- Optimizing caching and latency.
- Establishing service levels and incident response for AI services.
Capstone: Architecture for an AI-Driven Solution
- Defining context, component, and deployment views.
- Designing retrieval and agent orchestration.
- Developing security, governance, and cost plans.
- Conducting peer reviews, critiques, and creating migration roadmaps.
Requirements
- Experience in designing and maintaining production-grade software systems.
- Working knowledge of 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