World Congress 2025 • Aug 20, 2025 • Session details

Best practices: Building Enterprise Applications that leverage GenAI

Damir

Ready to ditch rigid UIs for natural language? Learn how RAG, Semantic Kernel, and function calling securely power enterprise apps without expensive model retraining.

Pause
Mute Enter Fullscreen
#1 about 2 min

Building enterprise artificial intelligence software in .NET

Integrating generative AI capabilities into enterprise systems requires understanding specific application frameworks and platforms like C#.

#2 about 5 min

Demonstrating natural language interactions with physical hardware

Leveraging semantic kernel bridges human language prompts seamlessly to practical software and hardware executions such as smart lighting.

#3 about 3 min

Mapping natural language prompts to PowerShell commands

User intents can accurately trigger command line scripts and system queries using integrated language models and plugins.

#4 about 2 min

Understanding embeddings and semantic token descriptions

Transforming tokens into mathematically measurable vectors enables systems to accurately gauge the semantic similarity between different texts.

#5 about 3 min

Storing and searching data with vector databases

Expanding massive array stores requires specialized databases capable of executing native vector distance functions efficiently to avoid heavy latency.

#6 about 2 min

Extending large language models without expensive retraining

Capabilities of pre-trained models are safely expanded using knowledge tools like retrieval augmented generation and action tools like function calling.

#7 about 4 min

Implementing text chunking and retrieval augmented generation

Custom C# applications calculate token consumption and segment raw text sequentially to map exact vector matches for incoming semantic queries.

#8 about 2 min

Overriding language model biases using custom vectors

Injecting custom business information directly into databases safely overwrites outdated training bias without incurring expensive retraining cycles.

#9 about 2 min

Executing system commands through model function calling

External plugins interpret tool assignments from the logic model to safely query APIs while tracking when sensitive data pipelines are touched.

#10 about 4 min

Building and debugging Semantic Kernel plugins programmatically

Detailed parameter descriptions inside backend classes ensure models accurately map natural language queries directly into system dependencies.

Matching moments

3:13 min

Embedding generative AI in enterprise software platforms

Mike Butcher Mike Butcher +3 · World Congress 2024

2:52 min

Scaling generative AI use cases across large enterprises

Mike Butcher Mike Butcher +3 · World Congress 2024

1:24 min

Expanding AI capabilities using retrieval-augmented generation

Cedric Clyburn Cedric Clyburn · World Congress 2024

8:55 min

Audience questions on data integration and future action models

Vijay Krishan Gupta +1 · LIVE

1:39 min

Balancing human-centric AI collaboration with environmental sustainability practices

Madalena Costa Madalena Costa · World Congress 2024

2:08 min

Navigating the components of the modern generative AI stack

Julián Duque Julián Duque · World Congress 2025