Course Outline
Architecture Foundations for AI Systems
- Layers, boundaries and separation of concerns
- Ports and adapters applied to AI components
- Quality attribute scenarios for AI features
- Architecture decision records as governance
Evolving an Existing Application
- Incremental modernisation instead of rewrite
- Placing AI services beside an existing monolith
- Strangler and anti-corruption layer patterns
- Integration seams for existing APIs and data
LLM Integration Architecture Patterns
- Model gateway as an abstraction boundary
- Synchronous, asynchronous and streaming integration
- Fallback, degradation and provider failover
- Prompt and model configuration as versioned assets
Contracts, APIs and Data Exchange
- Structured output schemas and validation
- Idempotency, retries and rate limiting
- Latency budgets and timeout orchestration
- Cost per request as an architectural constraint
RAG Architecture End to End
- Ingestion, chunking and embedding pipeline
- Index, retrieval, reranking and generation stages
- Retrieval placement relative to application services
- Trade-offs and failure modes at each stage
Vector Databases and Retrieval Design
- Managed versus self-hosted vector stores
- Dense, sparse and hybrid search
- Metadata filtering and tenant isolation
- Re-embedding strategy when models change
Retrieval Quality, Grounding and Evaluation
- Evaluation sets built from real queries
- Retrieval and answer quality metrics
- Citation, grounding and hallucination containment
- Feedback loops back into the index
Agent Architectures
- The agent loop and tool invocation
- Deterministic workflows versus autonomous planners
- Cases where an agent is the wrong answer
- Scoping agent responsibilities and state
Multi-Agent Systems and Orchestration
- Supervisor and orchestrator topologies
- Handoff protocols and message contracts
- Shared memory and context management
- Framework comparison on architectural grounds
Service Communication and Tool Protocols
- Event-driven and queue-based coordination
- Tool exposure through standard protocols
- Sagas, compensation and long-running transactions
- Observability across service hops
AI Agents in the Development Workflow
- Coding agents inside the delivery pipeline
- Spec-driven development and review gates
- Test generation and automated quality checks
- Guardrails that preserve architectural control
Governance and Software Quality
- Design review for AI features
- Model and prompt change management
- Regression evaluation as a pipeline stage
- Ownership, policy and approval paths
Security, Privacy and Data Governance
- Prompt injection and defence in depth
- Secrets, access control and least privilege
- Data residency, personal data and retention
- Auditability and human-in-the-loop controls
Scalability, Cost and Observability
- Tracing across agent chains
- Token and cost telemetry
- Caching and latency optimisation
- Service levels and incident response for AI services
Capstone: Architecture for an AI-Powered Solution
- Context, component and deployment views
- Retrieval and agent orchestration design
- Security, governance and cost plan
- Peer review, critique and migration roadmap
Requirements
- Experience designing and maintaining production software systems
- Working knowledge of REST APIs and service integration
- Familiarity with relational databases and data modelling
- Basic exposure to LLM-based tools or APIs
Audience
- Software architects
- Technical leads and senior engineers
- Engineering managers responsible for architecture decisions
Custom Corporate Training
Training solutions designed exclusively for businesses.
- Customized Content: We adapt the syllabus and practical exercises to the real goals and needs of your project.
- Flexible Schedule: Dates and times adapted to your team's agenda.
- Format: Online (live), In-company (at your offices), or Hybrid.
Price per private group, online live training, starting from 4800 € + VAT*
Contact us for an exact quote and to hear our latest promotions
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