World Congress 2025 • Aug 20, 2025 • Session details

Exploring LLMs across clouds

Tomislav Tipurić

Are you overpaying for enterprise AI infrastructure? Compare the distinct LLM architectures, RAG capabilities, and hidden pricing structures across Amazon, Google, and Microsoft to build autonomous agentic ecosystems.

Pause
Mute Enter Fullscreen
#1 about 3 min

The fundamental mechanics of large language models

How generative pre-trained transformers use probabilistic predictions and temperature settings to generate text.

#2 about 4 min

Evolution from text interfaces to agentic reasoning models

Tracking the transition from basic text chatbots to multimodal capabilities and autonomous agents.

#3 about 7 min

Comparing foundational AI models across major cloud providers

A breakdown of embedding, multimodal, and reasoning models offered by Amazon, Google, and Microsoft.

#4 about 4 min

Model performance leaderboards and API token pricing structures

Evaluating top model rankings on public arenas alongside an analysis of token-based input and output costs.

#5 about 5 min

Extending AI capabilities with retrieval augmented generation

Implementing knowledge engineering patterns and leveraging developer assistants to ground generative output in custom unstructured data.

#6 about 3 min

Semantic similarity and vector database search mechanics

How vector representations and orchestrators map semantic meaning to improve database retrieval accuracy.

#7 about 4 min

Cloud infrastructure supporting retrieval augmented generation ecosystems

Mapping the managed container environments, vector databases, and foundational AI solutions across major cloud ecosystems.

#8 about 2 min

Enterprise implementation scenarios for generative AI applications

Practical examples of deploying natural language understanding for contact center analytics and retail recommendation engines.

#9 about 2 min

Managing organizational change for AI developer productivity tools

Strategies for testing, documenting, and implementing generative coding assistants to improve engineering team velocity.

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

2:41 min

Transitioning artificial intelligence infrastructure into scalable commodity cloud services

juarezjunior juarezjunior · World Congress 2024

2:31 min

Integrating generative AI into cloud-native applications

Cedric Clyburn Cedric Clyburn · World Congress 2024

1:01 min

Understanding foundation models and generative AI capabilities

Timo Salm Timo Salm · World Congress 2025

3:23 min

The rapid evolution of generative artificial intelligence capabilities

Jens Echterling Jens Echterling · World Congress 2025