Training course · RAG & LLM Applications · Mobile Apps

RAG & LLM Applications for Mobile Developers

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

This course connects RAG & LLM Applications with the everyday processes of Mobile Apps. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

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.

Mobile development spans several worlds: Swift and SwiftUI for iOS, Kotlin and Jetpack Compose for Android, and cross-platform approaches with Flutter or React Native. On top come store guidelines, device fragmentation, offline capability, push notifications and demanding release processes. AI coding assistants and agents relieve teams of precisely these tasks: they build screens from designs, migrate UIKit or XML layouts to declarative UI frameworks, write UI and unit tests, analyse crash reports and automate build pipelines with Fastlane. Because mobile projects depend heavily on platform conventions, the AI needs precise context on architecture, state management and target platforms. This course shows you how to build that context and verify results on real devices.

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?

  • iOS developers using Swift and SwiftUI
  • Android developers using Kotlin and Jetpack Compose
  • Cross-platform developers using Flutter or React Native
  • Mobile teams in agencies and product companies
  • Tech leads responsible for app architecture and releases

Typical challenges we address

  • Maintaining several platforms in parallel with different languages and UI paradigms
  • Migrating from UIKit or XML layouts to declarative UI frameworks
  • Hard-to-reproduce crashes and performance issues across a wide range of devices
  • Laborious build, signing and store release processes

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 agents for screens, UI migrations and tests in native and cross-platform apps.
  • Diagnose crashes and performance issues faster and automate build and release processes with AI support.
  • Give the AI clear platform conventions and architecture rules and verify results on real devices.

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: Mobile Apps
  • Turning designs into screens
  • Declarative UI migration
  • Testing mobile apps
  • Analysing crash reports
  • Offline capability and data storage
  • Build and release automation
Module 7 Data protection, quality & transfer to daily work
  • Apps often handle sensitive device data such as location, contacts or health information, so generated code must request permissions sparingly and manage consent in line with GDPR. Signing keys, API keys and store credentials do not belong in prompts, and new SDKs and packages should be checked for licensing, tracking behaviour and supply-chain risk.
  • 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

Turning designs into screens

From screenshots or design specs, the assistant generates SwiftUI, Compose, Flutter or React Native screens that reuse your components, themes and navigation and respect dark mode and dynamic type.

Declarative UI migration

The agent moves UIKit view controllers or Android XML layouts to SwiftUI or Jetpack Compose step by step, wraps legacy parts via interop layers and protects behaviour with snapshot and UI tests.

Testing mobile apps

The AI writes unit tests for view models and repositories, UI tests with XCTest, Espresso or Flutter widget tests, and sets up mocks for networking and persistence.

Analysing crash reports

Symbolicated stack traces from crash reporting services are interpreted, likely causes such as threading or lifecycle issues narrowed down and fixes proposed alongside reproducing tests.

Offline capability and data storage

The assistant designs local persistence with Room, Core Data, SwiftData or SQLite, sync logic with conflict handling and robust networking layers with retries and caching.

Build and release automation

Fastlane lanes, Gradle configuration and CI workflows for builds, signing, beta distribution and store uploads are created or repaired, including versioning and release notes. Expiring certificates are flagged early.

Possible hands-on projects

Stocktake app with barcode scanner

A Flutter or React Native app that scans barcodes, records items offline and syncs them with a REST API once a connection is available.

SwiftUI habit tracker

An iOS app with SwiftUI, local persistence, widgets and local notifications, developed entirely with an AI agent. Habits and progress are displayed in clear charts.

Compose feedback form

An Android app built with Jetpack Compose that captures forms with photo attachments, caches them offline and submits them to a back end – with UI tests.

Prerequisites

Solid programming skills in Python (or TypeScript as an alternative), basic knowledge of databases and REST APIs, and some experience with LLM APIs. Hands-on app development experience with Swift, Kotlin, Dart or React Native, plus Xcode or Android Studio and Git.

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

Apps often handle sensitive device data such as location, contacts or health information, so generated code must request permissions sparingly and manage consent in line with GDPR. Signing keys, API keys and store credentials do not belong in prompts, and new SDKs and packages should be checked for licensing, tracking behaviour and supply-chain risk.

Suggested dates

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

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Mon, 30 November 2026 – Tue, 1 December 2026 Augsburg Request
  • Mon, 14 December 2026 – Tue, 15 December 2026 Online Request
  • Wed, 13 January 2027 – Thu, 14 January 2027 Online Request
  • Thu, 21 January 2027 – Fri, 22 January 2027 Kaiserslautern Request
  • Thu, 28 January 2027 – Fri, 29 January 2027 Online 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.

Does the course cover iOS, Android and cross-platform equally?

Yes. Working with AI assistants follows the same principles on every platform: provide context, scope tasks and test the results. In the exercises you choose your focus – Swift, Kotlin, Flutter or React Native – and tackle typical tasks for your platform, so mixed teams benefit just as much as specialists.

Can AI work with Xcode and Android Studio?

Many AI assistants can be used inside Android Studio or alongside Xcode, and agents also work from the command line with xcodebuild, Gradle or the Flutter CLI. We show you how to drive builds, tests and simulators so that the agent can check its own results and fix errors iteratively.

How much does “RAG & LLM Applications for Mobile Developers” 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 Mobile Developers

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