Section 1. Architecture and Business1. Context of an Architect's Work- Essence and Context: Architecture definition, types (Solution, Enterprise, System), and value creation.
- Methodologies and Stakeholders: Adapting frameworks (TOGAF, Zachman) and stakeholder expectation management.
- Paradigm Shift in the AI Era:
1. Code as Liability: Shifting focus from writing to verification and integration.
2. Probabilistic Architecture: Designing non-deterministic systems and risk management.
3. Domain Authority: Deep business understanding is more important than syntax.
4. Guardrails: Setting boundaries for autonomous agents.
5. New Primitives: Multi-agent systems, RAG, MCP.
6. AI-Readiness: Designing systems understandable for AI (Documentation as Code).
2. Requirements Management- Classical Requirements: Functional, non-functional, constraints, and Utility tree.
- Intent Formulation: Formulating intentions and goals for AI agents instead of rigid scripts.
- New NFRs for AI Systems:
1. Probabilistic outcomes: Working with non-deterministic behavior.
2. Latency & UX: Specifics of streaming and long-running operations.
3. Cost constraints: Token economics.
4. Safety & Alignment: Protection against injections and ethical constraints.
3. Technological Strategy and Architecture- Styles and Patterns: Monolith, microservices, EDA, serverless, and distributed system patterns.
- Quality and Tactics: Ensuring Availability, Performance, and Scalability in distributed systems.
- Strategy and Development: Technological strategy, Roadmap, and Reference Architecture.
- Change Management: Working with stakeholders, initiatives, and implementing changes.
- Design Process: Decision-making algorithms and typical architectural solutions.
Section 2. Architecture in the AI Era4. AI Architectural Stack: Foundation Models and Infrastructure 1. Foundation Models (LLM, LMM, SLM): Selection criteria.
2. Orchestration Frameworks: Role in architecture.
3. Vector Databases & RAG Infrastructure: Architectural patterns for knowledge storage.
4. Serving Layer: API Gateway for AI, Caching, Rate limiting.
- Interaction Patterns: Prompt engineering vs. fine-tuning vs. RAG — when and what to apply.
- Infrastructure Challenges: GPU vs. CPU inference, quantization, self-hosting vs. API.
- Data Strategy for AI: Preparing unstructured data, data pipelines for embeddings.
5. Designing Agents, Multi-Agent Systems, and Tools (MCP)- From Single Prompts to Agents: Cognitive architecture pattern: designing memory, planning, and tools.
- Agent Types: ReAct, Plan-and-Solve, Reflexion.
- Agent Orchestration:
1. Interaction patterns: Hierarchical, Collaborative, Competitive.
2. State management and context transfer between agents.
- Model Context Protocol (MCP):
1. Standardizing data connection to LLMs.
2. MCP server and client architecture.
3. Securely providing tools to agents.
- Complexity and Debugging: Chain of Thought tracing, Observability for agents.
6. Operational AI Architecture: FinOps, Security, and Quality 1. Pricing models (per token, per hour, provisioned throughput).
2. Cost monitoring and optimization (Caching, Routing, Model cascading).
3. Unit economics of AI features.
1. Attack vectors: Prompt Injection, Jailbreak, Data Poisoning.
2. Architectural defense patterns: Input/Output Guardrails, Sanitization layers.
3. Privacy Preserving AI: PII masking, Local processing.
1. Paradigm shift in testing: From Unit tests to Evals (evaluating generation quality).
2. Metrics: RAGAS, BLEU/ROUGE (where applicable), LLM-as-a-judge.
3. Dataset management: Creating Golden Datasets for change validation.
7. Advanced Patterns, Optimization, and AI-assisted Design- Architecting with AI: Using AI during system design.
- Optimization Techniques:
1. Prompt optimization and Prompt Caching.
2. Speculative decoding and request parallelization.
3. Distillation: Transferring knowledge from a large model to a smaller one for speed and cost.
- Probabilistic Engineering:
1. Uncertainty management: Retry policies, Fallback strategies.
2. Architectural antipatterns: Hallucination amplification, Context overflow.
3. Hybrid architectures: Neuro-symbolic approaches (combining code and LLM).
Section 3. Organization, Communication, and Culture8. Organizational Analysis- Structure and Culture: Types of culture, values, and finding your place in the organization.
- Expectation Management and Career: Goals, agreements, and an architect's path.
- Stakeholder Management: Identifying key individuals and managing their influence.
- Reality and Antipatterns: Cursed roles, sabotage of solutions, inflated expectations, and incompetence.
9. Trust in the Architect and Justification of Decisions- Trust and Influence: Boundaries of responsibility, demonstrating vision, and earning trust.
- Communication: Effective interaction with business, the team, and infrastructure.
- Decision Making: Comparison tables, justification of choices, and preventing unnecessary questions.
- Presentation and Sales: Techniques for defending architectural solutions.
- Pet Projects: The role of personal practice in development and authority.
10. Architectural Process- Artifacts and Standards: Strategy, Roadmap, ADR, HLD/LLD, and templates (Architecture Proposal).
- Collaborative Design: Event Storming, DDD, and Cross-review of solutions.
- Documentation as Context: Creating documentation understandable to humans and AI agents (RAG).
- MCP and Tools: Context standardization and architectural support tools.
- Shift from Creation to Review: Changing role to validating AI solutions and finding logical errors.
- Governance: Hierarchy of architects, Architecture Board, and standards.
- Processes in Reality: Working with legacy documentation, resistance, and tacit knowledge.
11. Evolution of Architecture in the Real World- Company Evolution: From a startup (10-50 engineers) to an enterprise (500+ engineers).
- Project Types: Outsource, product development, integration, and digital transformation.
- Legacy and Tech Debt: Refactoring strategies and balancing with new features.
- AI in the Real World:
1. Legacy + AI: Using AI for refactoring (auto-tests, code explanation).
2. Buy vs. Build in AI: Strategy selection (Proprietary Models vs. Open Source).
- Complex Situations: Conflicts with product/infra, changing an architect, and burnout.
12. Trends and Transformation of the Architect Profession- Threats and Opportunities: Will AI replace the architect?
- Shift in Competency Profile:
1. Decreased weight of pure coding.
2. Growing importance of systems thinking, Data Science, and ethics.
1. AI Architect / AI Solution Architect.
2. Prompt Architect / Engineer.
3. Chief AI Officer (CAIO).
- Learning Strategy: What to learn right now and what can be postponed.
- Working in Hybrid Teams: Interacting with AI agents as new team members.
- Impact on the Job Market: Changing salary ranges, demand for integrator architects.
- Future of Tools: From IDEs to Agentic Development Environments and the role of the architect in setting up the development environment.