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.
- Using architecture decision records for effective governance.
Modernizing Existing Applications
- Implementing incremental modernization strategies rather than full rewrites.
- Positioning AI services alongside existing monolithic structures.
- Utilizing strangler and anti-corruption layer patterns.
- Creating integration seams for current APIs and data sources.
LLM Integration Architectural Patterns
- Establishing a model gateway as a key abstraction boundary.
- Managing synchronous, asynchronous, and streaming integrations.
- Implementing fallback, degradation, and provider failover mechanisms.
- Treating prompt and model configurations as versioned assets.
Contracts, APIs, and Data Exchange
- Defining structured output schemas and validation rules.
- Ensuring idempotency, handling retries, and applying rate limiting.
- Setting latency budgets and orchestrating timeouts.
- Treating cost per request as a critical architectural constraint.
End-to-End RAG Architecture
- Building the ingestion, chunking, and embedding pipeline.
- Designing the index, retrieval, reranking, and generation stages.
- Determining retrieval placement relative to application services.
- Analyzing trade-offs and failure modes at each stage.
Vector Databases and Retrieval Design
- Evaluating managed versus self-hosted vector stores.
- Implementing dense, sparse, and hybrid search capabilities.
- Applying metadata filtering and ensuring tenant isolation.
- Developing re-embedding strategies for model changes.
Retrieval Quality, Grounding, and Evaluation
- Constructing evaluation sets based on real-world queries.
- Measuring retrieval and answer quality metrics.
- Managing citations, grounding, and containing hallucinations.
- Establishing feedback loops that refine the index.
Agent Architectures
- Understanding the agent loop and tool invocation processes.
- Comparing deterministic workflows with autonomous planners.
- Identifying scenarios where an agent is inappropriate.
- Defining the scope of agent responsibilities and state.
Multi-Agent Systems and Orchestration
- Designing supervisor and orchestrator topologies.
- Establishing handoff protocols and message contracts.
- Managing shared memory and context effectively.
- Comparing frameworks based on architectural merits.
Service Communication and Tool Protocols
- Implementing event-driven and queue-based coordination.
- Exposing tools through standard protocols.
- Managing sagas, compensation, and long-running transactions.
- Ensuring observability across service interactions.
AI Agents in Development Workflows
- Integrating coding agents into the delivery pipeline.
- Adopting spec-driven development and review gates.
- Generating tests and automating quality checks.
- Implementing 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, policy, and approval workflows.
Security, Privacy, and Data Governance
- Addressing prompt injection and defense-in-depth strategies.
- Managing secrets, access control, and least privilege.
- Ensuring data residency, handling personal data, and managing retention.
- Maintaining auditability and human-in-the-loop controls.
Scalability, Cost, and Observability
- Tracing processes across agent chains.
- Monitoring token and cost telemetry.
- Optimizing caching and latency performance.
- Defining service levels and incident response for AI services.
Capstone: Architecting an AI-Driven Solution
- Developing context, component, and deployment views.
- Designing retrieval and agent orchestration strategies.
- Formulating a plan for security, governance, and cost.
- Conducting peer reviews, critiques, and creating migration roadmaps.
Requirements
- Practical experience in designing and maintaining production-grade software systems.
- Proficient knowledge of REST APIs and service integration techniques.
- Understanding of relational databases and data modeling concepts.
- Familiarity with LLM-based tools or APIs.
Intended Audience
- Software architects.
- Technical leads and senior engineers.
- Engineering managers accountable 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