Training course · RAG & LLM Applications · Software Architecture

RAG & LLM Applications for Software Architects

Develop RAG and LLM applications: embeddings, vector databases, chunking, retrieval, evaluation, cost control and data protection.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

“RAG & LLM Applications for Software Architects” is a hands-on course for roles such as Software architects and solution architects, Enterprise architects with links to application development and Senior developers and tech leads with architectural responsibility. Rather than learning RAG & LLM Applications in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from Software Architecture.

Retrieval-augmented generation connects language models to your own knowledge: manuals, contracts, tickets, wikis or product data are made searchable and handed to the model as context at runtime. The result is assistants that give grounded answers with citations instead of hallucinating. In this two-day course you build a complete RAG pipeline, from document preparation through embeddings and a vector database to answer generation, and you learn which levers actually determine quality.

Day two takes you from prototype to robust application. You compare chunking strategies, combine semantic and lexical search, apply reranking, metadata filters and query rewriting, and measure the effect with systematic evaluations. You also cover prompt caching, cost control, latency optimisation, document-level access control and privacy-compliant operation with an eye on GDPR and the EU AI Act. By the end you know when classic RAG is enough, when a large context window or agentic retrieval is the better option, and how to justify your architecture choices.

When AI agents write large parts of the code, architecture becomes more important, not less: clear module boundaries, documented decisions and verifiable quality goals are the frame that keeps generated code consistent. AI assistants also support architects directly, for example by analysing existing codebases, producing C4 diagrams, drafting architecture decision records and weighing alternatives against quality attributes. Fitness functions and architecture tests can be generated and anchored in your pipelines. In this course you learn to use AI as a sparring partner for architectural decisions, prepare architectural knowledge so that coding agents follow it reliably and spot erosion early in fast-growing codebases.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Software architects and solution architects
  • Enterprise architects with links to application development
  • Senior developers and tech leads with architectural responsibility
  • Platform and cloud architects
  • Owners of architecture governance and review boards

Typical challenges we address

  • Architecture documentation goes stale quickly and drifts from the actual code
  • Decisions are made verbally and their context is lost
  • Gradual architectural erosion through cyclic dependencies and violated layer boundaries
  • Without clear guidance, AI-generated code ignores established patterns and conventions

What you will be able to do

  • You build a complete RAG pipeline from document preparation to answers with citations.
  • You choose embedding model, chunking strategy and vector database on solid grounds.
  • You improve retrieval quality with hybrid search, reranking and metadata filters.
  • You measure application quality with systematic evaluations and detect regressions.
  • Use AI to analyse existing systems, evaluate architectural options and record decisions as ADRs.
  • Anchor architecture rules as fitness functions in the pipeline and detect erosion early.
  • Shape context and rules so that AI coding agents reliably respect your architectural guidelines.

Course outline

Day 1

Module 1 Foundations of RAG and LLM applications
  • Anatomy of a RAG pipeline: ingestion, indexing, retrieval, generation
  • Understanding embeddings: semantic similarity, dimensions, model selection
  • Weighing RAG against fine-tuning and long context windows
  • Structured outputs, citations and dealing with hallucinations
Module 2 Document preparation and chunking
  • Reliably extracting PDFs, Office documents, HTML and tables
  • Chunking strategies: fixed size, structure-aware, semantic, with overlap
  • Enriching metadata and generating contextual summaries per chunk
  • Incremental updates and deletion of documents in the index
Module 3 Vector databases and retrieval strategies
  • Comparing vector databases and extensions such as pgvector, Qdrant, Weaviate or OpenSearch
  • Hybrid search combining vector and full-text search with BM25
  • Reranking, metadata filtering and query rewriting
  • Agentic retrieval: letting the model decide on search steps and tools
Module 4 Evaluation and quality assurance
  • Building and maintaining test sets from real user questions
  • Retrieval metrics such as recall and precision, and answer metrics such as faithfulness
  • Using and calibrating LLM-as-a-judge sensibly
  • Regression testing when chunking, model or prompt changes

Day 2

Module 5 Operations, cost and data protection
  • Prompt caching, batch processing and model choice to cut costs
  • Optimising latency and streaming responses
  • Document-level permissions, tenant isolation and protection against prompt injection
  • Data protection: data residency, processing agreements, deletion policies, GDPR and the EU AI Act
Module 6 Practice lab: Software Architecture
  • Documenting architecture decisions
  • Reconstructing existing architecture
  • Evaluating alternatives
  • Generating fitness functions
  • Guardrails for coding agents
  • Carving out domains
Module 7 Data protection, quality & transfer to daily work
  • Architecture documents often describe security-relevant details such as network zones and data flows: you learn which information may be shared with AI services, how to assess licensing risks of components and how architectural decisions traceably reflect GDPR, NIS2 and Cyber Resilience Act requirements.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Documenting architecture decisions

Turn discussions, meeting notes and pull requests into structured architecture decision records with context, options considered, decision and consequences, stored consistently in the repository. Related decisions are linked automatically.

Reconstructing existing architecture

Analyse existing codebases, extract modules, dependencies and interfaces and generate up-to-date C4 diagrams as diagrams-as-code with PlantUML, Mermaid or Structurizr. Diagrams can be refreshed automatically on every build.

Evaluating alternatives

Compare options such as a modular monolith, microservices or event-driven integration against quality scenarios, cost and team structure, and make trade-offs visible following ATAM principles.

Generating fitness functions

Express architecture rules such as layer access, forbidden dependencies or naming conventions as automated tests with ArchUnit, dependency-cruiser or similar tools and wire them into CI.

Guardrails for coding agents

Describe architectural principles, module boundaries and patterns in rule files and context documents so AI agents follow them reliably when generating code, and spot deviations in review.

Carving out domains

Derive bounded contexts, aggregates and context maps following domain-driven design from event storming results and business descriptions, and use them to shape teams and services.

Possible hands-on projects

ADR assistant

A command-line tool that turns bullet points into a complete ADR from a template, links related decisions and updates an index in the repository.

Dependency visualiser

A script that analyses import relationships in a codebase, flags cycles and layer violations and renders an interactive diagram in the browser.

Architecture Q&A over repos

A small application that indexes ADRs, diagrams and code and answers architecture questions with references to the underlying sources. New team members onboard faster.

Prerequisites

Solid programming skills in Python (or TypeScript as an alternative), basic knowledge of databases and REST APIs, and some experience with LLM APIs. You have several years of development experience and have made or supported architectural decisions in larger software systems.

Technical requirements

A laptop with Python, Git, Docker and a code editor, plus API access to at least one LLM and embedding provider. Credentials for the exercises can be provided if needed.

Data protection & compliance

Architecture documents often describe security-relevant details such as network zones and data flows: you learn which information may be shared with AI services, how to assess licensing risks of components and how architectural decisions traceably reflect GDPR, NIS2 and Cyber Resilience Act requirements.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Thu, 10 December 2026 – Fri, 11 December 2026 Salzburg Request
  • Mon, 14 December 2026 – Tue, 15 December 2026 Online Request
  • Tue, 12 January 2027 – Wed, 13 January 2027 Bremen Request
  • Tue, 19 January 2027 – Wed, 20 January 2027 Online Request
  • Thu, 4 February 2027 – Fri, 5 February 2027 Augsburg Request

Frequently asked questions

When is RAG better than fine-tuning?

RAG is the right choice when a model needs access to current, extensive or frequently changing knowledge and should cite its sources. Fine-tuning mainly changes style, format or specialised behaviour. In many projects RAG is the faster, cheaper and more controllable route, sometimes complemented by fine-tuning for niche tasks.

Which vector database should we use?

That depends on data volume, existing infrastructure, filtering needs and operating model. If you already run PostgreSQL, pgvector often takes you a long way, while specialised systems shine with large datasets and hybrid search. In the course you compare several options hands-on and derive criteria for your own decision.

How can RAG be run in a GDPR-compliant way?

Key factors are choosing providers with suitable data residency and a data processing agreement, enforcing document-level permissions, having a deletion policy for the index and logs, and minimising personal data. For highly sensitive data, self-hosted models are also an option. We work through these choices using realistic architectures.

Can AI make architecture decisions?

AI is a strong sparring partner: it offers options, names trade-offs, finds gaps in reasoning and documents decisions in a structured way. Responsibility stays with people, because architecture depends on business context, team skills, budget and risk appetite. In the course you learn to use AI so that decisions are better reasoned and made faster.

How do we stop AI agents from eroding the architecture?

Through a combination of clear context and automated checks: rule files and ADRs describe module boundaries and patterns, fitness functions and architecture tests in CI block violations, and reviews focus on structural changes. Architecture thus turns from documentation into a verifiable guardrail for humans and agents alike.

How much does “RAG & LLM Applications for Software Architects” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Software Architects

More RAG & LLM Applications courses

All 29 RAG & LLM Applications courses

RAG & LLM Applications · MunichRAG & LLM Applications · SalzburgRAG & LLM Applications · BerlinRAG & LLM Applications · AugsburgRAG & LLM Applications · HanoverRAG & LLM Applications · BremenRAG & LLM Applications · StuttgartRAG & LLM Applications · KaiserslauternRAG & LLM Applications · Online