In the journey to accelerate AI agent development and enhance chatbot capabilities, the team structure that we put in place played a key role. Organizing teams in proper structures goes a long way in helping with faster development cycles and collaboration. Here is a simplified view of our team structure:

LMOS has been instrumental in the development and success of Deutsche Telekom’s chatbot, “Frag Magenta". In this blog, we showcase how LMOS has accelerated the journey of Frag Magenta chatbot with some key performance metrics.

In a world increasingly powered by AI, creating reliable and efficient agents isn’t just about technology but also about processes, strucutures and methodologies. This blog will take you behind the scenes of our agent development, and the various phases involved until production rollout.

As the world of AI continues to evolve and develop, the need of integration of AI services into your applications has become increasingly valuable.

Since ARC's goal is to make the process of integration, management and creation of AI in your existing services as seamless as possible it only made sense to integrate Spring.AI to work in a plug and play fashion.

Meta have released a new version of their large language model, Llama3, https://ai.meta.com/blog/meta-llama-3/.

Thanks to ollama, the model can easily be tested locally, see https://ollama.com/library/llama3