Kurzusleírás
Foundations of Architecture for AI Systems
- Layers, boundaries, and separation of concerns
- Application of ports and adapters to AI components
- Quality attribute scenarios specific to AI features
- Architecture decision records as a governance mechanism
Evolving Existing Applications
- Incremental modernization approaches instead of full rewrites
- Integrating AI services alongside existing monoliths
- Strangler and anti-corruption layer patterns
- Integration points for existing APIs and data structures
Architectural Patterns for LLM Integration
- Model gateways as abstraction boundaries
- Synchronous, asynchronous, and streaming integration methods
- Fallback strategies, degradation, and provider failover
- Managing prompt and model configurations as versioned assets
Contracts, APIs, and Data Exchange
- Structured output schemas and validation mechanisms
- Idempotency, retries, and rate limiting strategies
- Latency budgets and timeout orchestration
- 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
- 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
- Re-embedding strategies when models change
Retrieval Quality, Grounding, and Evaluation
- Building evaluation sets from real-world queries
- Metrics for retrieval and answer quality
- Citation, grounding, and containment of hallucinations
- Feedback loops integrated into the index
Agent Architectures
- The agent loop and tool invocation processes
- Deterministic workflows versus autonomous planners
- Identifying cases where an agent is inappropriate
- Defining 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 grounds
Service Communication and Tool Protocols
- Event-driven and queue-based coordination
- Exposing tools through standard protocols
- Sagas, compensation, and long-running transactions
- Observability across service hops
AI Agents in the Development Workflow
- Integrating coding agents into the delivery pipeline
- Spec-driven development and review gates
- Test generation and automated quality checks
- Guardrails that maintain architectural control
Governance and Software Quality
- Design reviews for AI features
- Change management for models and prompts
- Regression evaluation as a pipeline stage
- Ownership, policy, and approval pathways
Security, Privacy, and Data Governance
- Defending against prompt injection and implementing defense in depth
- Secrets management, access control, and least privilege
- Data residency, personal data, and retention policies
- Auditability and human-in-the-loop controls
Scalability, Cost, and Observability
- Tracing across agent chains
- Token and cost telemetry
- Caching and latency optimization
- Service levels and incident response for AI services
Capstone: Architecture for an AI-Driven Solution
- Context, component, and deployment views
- Design of retrieval and agent orchestration
- Security, governance, and cost planning
- Peer review, critique, and migration roadmap
Követelmények
- Tapasztalat production szoftverrendszerek tervezésében és karbantartásában
- Munkaképes ismeretek REST API-k és szolgáltatásintegráció terén
- Familiaritás relációs adatbázisokkal és adatomodellázással
- Alapszintű ismeretek LLM-alapú eszközök vagy API-k terén
Célcsoport
- Szoftverarchitektusok
- Technikai vezetők és senior fejlesztők
- Fejlesztési menedzserek, felelősök az architektúrális döntésekért
Vélemények (1)
Hogy megszereztem tudást a Python Streamlit könyvtárról, és biztosan megpróbálom használni annak érdekében, hogy fejlesszem a csapatomban használt R Shiny alkalmazásokat.
Michal Maj - XL Catlin Services SE (AXA XL)
Kurzus - GitHub Copilot for Developers
Gépi fordítás