Talk | 
EKON 29
 | 27.10.2025

AI Agents in Action: LLMs, Tools und Reasoning

Nach Chatbots sind Agents und Multi-Agent-Systeme nun das nächste große Ding in der Welt der Generativen KI. Mit Hilfe von Tools, einem "Gedächtnis" und bewährten AI-Patterns zeigt Ihnen Sebastian Gingter in dieser Session, wie Sie aus Large Language Models richtig intelligente, autonom handelnde Systeme bauen können. Diese Agents sind in der Lage, über ein komplexes Problem nachzudenken, einen Lösungsplan zu entwerfen und dann auch auszuführen - ein bisschen Texte generieren war gestern. Mit einer Mischung aus Theorie, praxisnahen Code-Beispielen und Architekturansätzen beleuchtet Sebastian nicht nur die Abgrenzung zu einfachen LLM-Aufrufen und Agentic Workflows - er zeigt auch sowohl  Möglichkeiten als auch die Grenzen aktueller Technologien. Ist das nächste Level schon zum Greifen nah, oder fehlt da noch etwas, um praxistauglich zu werden?

Sebastian ist Consultant bei Thinktecture und Microsoft MVP. Seine Spezialgebiete sind Generative AI im Businessumfeld sowie ASP.NET Core.

Event

EKON 29
27.10.25  
- 29.10.25 
@ Düsseldorf
 (DE)

Slidedeck

Weitere Artikel zu aktuellen Schwerpunkten

.NET
pg

Discriminated Unions in .NET: Integration with Frameworks and Libraries

A key aspect of adopting any new pattern is understanding how it interacts with the surrounding application infrastructure. When using Discriminated Unions, questions arise: How can a Result union be serialized to JSON? How can an OrderState union be persisted using Entity Framework Core? This article explores practical integration strategies with common .NET frameworks.
02.11.2025
.NET
pg

Advanced Value Object Patterns in .NET

While basic value objects solve primitive obsession, complex domain requirements need sophisticated modeling techniques. This article explores advanced patterns using Thinktecture.Runtime.Extensions to tackle real-world scenarios: open-ended dates for employment contracts, composite file identifiers across storage systems, recurring anniversaries without year components, and geographical jurisdictions using discriminated unions.
19.10.2025
.NET
pg

Discriminated Unions in .NET: Modeling States and Variants

Domain models often involve concepts that exist in multiple distinct states or variations. Traditional approaches using enums and nullable properties can lead to invalid states and scattered logic. This article explores how discriminated unions provide a structured, type-safe way to model domain variants in .NET, aligning perfectly with Domain-Driven Design principles while enforcing invariants at the type level.
06.10.2025
.NET
pg

Smart Enums in .NET: Integration with Frameworks and Libraries

Learn how to seamlessly integrate Smart Enums with essential .NET frameworks and libraries. This article covers practical solutions for JSON serialization, ASP.NET Core model binding for both Minimal APIs and MVC controllers, and Entity Framework Core persistence using value converters. Discover how Thinktecture.Runtime.Extensions provides dedicated packages to eliminate integration friction and maintain type safety across your application stack.
21.09.2025
.NET
pg

Value Objects in .NET: Enhancing Business Semantics

Value objects are fundamental building blocks in Domain-Driven Design, serving far more than simple data wrappers. This article explores their strategic importance in bridging technical code and business concepts, enforcing domain rules, and fostering clearer communication with domain experts. Learn how to build robust aggregates, cultivate ubiquitous language, and encapsulate domain-specific behavior using Thinktecture.Runtime.Extensions in .NET applications.
16.09.2025
.NET
pg

Pattern Matching with Discriminated Unions in .NET

Traditional C# pattern matching with switch statements and if/else chains is error-prone and doesn't guarantee exhaustive handling of all cases. When you add new types or states, it's easy to miss updating conditional logic, leading to runtime bugs. The library Thinktecture.Runtime.Extensions solves this with built-in Switch and Map methods for discriminated unions that enforce compile-time exhaustiveness checking.
26.08.2025

Unsere Webinare

Unsere Artikel

Mehr über uns