Training course · RAG & LLM Applications · Internal Tools & Automation

RAG & LLM Applications for Internal Tools and Automation

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 Internal Tools & Automation. 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.

Almost every company has a long backlog of small tools nobody gets round to building: admin interfaces for master data, scripts for recurring data reconciliation, Slack or Teams bots, report generators and glue between SaaS systems. With AI coding assistants and agents, internal tools like these can be built in hours rather than weeks. Developers, ops and platform teams therefore shift their focus from writing code to clear requirements, secure access and reliable operation. Internal tools in particular often hold far-reaching rights over production data and quickly become business-critical. In this course you learn to build internal tools and automations rapidly with AI, implement authentication and permissions correctly from the start and design solutions that stay documented, tested and maintainable.

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 developers maintaining internal applications and scripts
  • DevOps, SRE and platform teams
  • IT administrators with automation responsibilities
  • Operations and RevOps engineers
  • Business process automation teams

Typical challenges we address

  • A long backlog of internal tools that never get prioritised next to product work
  • Manual reconciliation between SaaS systems, spreadsheets and databases that is prone to error
  • Internal tools with excessive permissions, no logging and no clear owner
  • Undocumented scripts that only one person understands

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.
  • Build internal tools, bots and automations with AI agents quickly and to a solid standard.
  • Implement authentication, permissions, logging and secrets management correctly from the outset.
  • Design automations that are documented, testable and operable, so they do not depend on individual people.

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: Internal Tools & Automation
  • Generating admin interfaces
  • Automating data reconciliation
  • Chat bots for teams
  • Automating ops runbooks
  • Generating reports and exports
  • Building agent workflows
Module 7 Data protection, quality & transfer to daily work
  • Internal tools often access employee, customer and production data: you learn to grant permissions on a least-privilege basis, keep secrets in vaults rather than code, log access and take GDPR and works council requirements into account for tools that touch employee data.
  • 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

Generating admin interfaces

Create CRUD interfaces from a database schema or API with search, filters, validation, role-based permissions and an audit log, so business teams can maintain master data safely.

Automating data reconciliation

Write scripts that regularly pull data from CRM, ERP, ticketing systems and spreadsheets, reconcile it and report discrepancies, with retry logic, idempotency and clear error messages.

Chat bots for teams

Build Slack or Teams bots that answer status queries, trigger approvals, announce deployments or provide on-call information while only executing explicitly permitted actions. Every action is logged with the user ID.

Automating ops runbooks

Turn recurring operational tasks such as user management, certificate renewal or log analysis into reviewed scripts and workflows, safeguarded with a dry-run mode and logging.

Generating reports and exports

Automatically prepare regular analyses from databases and APIs as PDF, spreadsheet or email, including scheduling, parameters and traceable data sources. Manual copy-and-paste between systems disappears entirely.

Building agent workflows

Connect AI agents to tools such as the ticketing system, knowledge base and internal APIs, for example via MCP, to pre-qualify requests, gather data and prepare drafts for human approval.

Possible hands-on projects

Onboarding automation

A workflow that creates accounts in several systems for new starters, assigns groups and sends the line manager a checklist of outstanding steps.

Licence overview

An internal dashboard that pulls usage data from SaaS tools, flags unused licences and shows costs per team at a glance.

Deployment bot

A chat bot that announces deployments, summarises changes from pull requests and notifies the right people when a pipeline fails.

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 programming experience in a language such as Python, TypeScript or Go and know the basics of APIs, databases and the command line.

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

Internal tools often access employee, customer and production data: you learn to grant permissions on a least-privilege basis, keep secrets in vaults rather than code, log access and take GDPR and works council requirements into account for tools that touch employee data.

Suggested dates

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

  • Tue, 24 November 2026 – Wed, 25 November 2026 Online Request
  • Thu, 3 December 2026 – Fri, 4 December 2026 Hanover Request
  • Mon, 14 December 2026 – Tue, 15 December 2026 Online Request
  • Mon, 11 January 2027 – Tue, 12 January 2027 Munich Request
  • Mon, 18 January 2027 – Tue, 19 January 2027 Online Request
  • Thu, 4 February 2027 – Fri, 5 February 2027 Stuttgart 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.

When is a custom internal tool better than an off-the-shelf product?

When a process is specific to your organisation, spans several systems or standard tools only fit after heavy customisation. AI cuts development cost considerably, but operation and maintenance remain. In the course you learn to weigh effort against benefit realistically and build tools that keep working with minimal upkeep.

How do we secure internal tools that were built quickly with AI?

With fixed guardrails: sign-in through your central identity provider, role-based permissions, no secrets in code, logging of every write action and a short review before go-live. These building blocks can be stored as a template so AI agents include them automatically in every new tool. You create exactly these templates in the course.

How much does “RAG & LLM Applications for Internal Tools and Automation” 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 Internal Tools and Automation

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