BrianSletten

We have seen how Retrieval Augmented Generation (RAG) systems can help prop up Large Language Models (LLMs) to avoid some of their worst tendencies. But that is just the beginning. The cutting edge stateoftheart systems are Multimodal and Agentic, involving additional models, tools, and reusable agents to break problems down in separate pieces, transform and aggregate the results, and validate the results before returning them to the user. Come get introduced to some of the latest and greatest techniques for maximizing the value of your LLMbased systems while minimizing the risk.

We have seen how Retrieval Augmented Generation (RAG) systems can help prop up Large Language Models (LLMs) to avoid some of their worst tendencies. But that is just the beginning. The cutting edge stateoftheart systems are Multimodal and Agentic, involving additional models, tools, and reusable agents to break problems down in separate pieces, transform and aggregate the results, and validate the results before returning them to the user. Come get introduced to some of the latest and greatest techniques for maximizing the value of your LLMbased systems while minimizing the risk.

A client once asked me to take a team that was new to REST, Agile, etc. and put together a high profile, high value commerce-oriented API in the period of six months. In the process of training the team and designing this API, I hit upon the idea of providing rich testing coverage by mixing the Behavior-Driven Design testing approach with REST.

Large Language Models (LLMs) such as ChatGPT and Llama have impressed us with what they can do. They have also horrified us with what they actually do when they are employed with no protection: hallucinations, stale knowledge bases, no conceptual basis for reasoning, and a capacity for toxic and inappropriate content generation. Rather than avoid them altogether or risk legal liability or brand damage, we can put some guardrails around them to benefit from their best traits without fearing their worst. Retrieval Augmented Generation (RAG) systems augment the process to make it behave more to our liking. Come hear what you can do to benefit from AI systems without fearing them.

Large Language Models (LLMs) such as ChatGPT and Llama have impressed us with what they can do. They have also horrified us with what they actually do when they are employed with no protection: hallucinations, stale knowledge bases, no conceptual basis for reasoning, and a capacity for toxic and inappropriate content generation. Rather than avoid them altogether or risk legal liability or brand damage, we can put some guardrails around them to benefit from their best traits without fearing their worst. Retrieval Augmented Generation (RAG) systems augment the process to make it behave more to our liking. Come hear what you can do to benefit from AI systems without fearing them.

If you are getting tired of the appearance of new types of databases... too bad. We are increasingly relying on a variety of data storage and retrieval systems for specific purposes. Data does not have a single shape and indexing strategies that work for one are not necessarily good fits for others. So after hierarchical, relational, object, graph, columnoriented, document, temporal, appendonly, and everything else, get ready for Vector Databases to assist in the systematization of machine learning systems.

If you are getting tired of the appearance of new types of databases... too bad. We are increasingly relying on a variety of data storage and retrieval systems for specific purposes. Data does not have a single shape and indexing strategies that work for one are not necessarily good fits for others. So after hierarchical, relational, object, graph, columnoriented, document, temporal, appendonly, and everything else, get ready for Vector Databases to assist in the systematization of machine learning systems.

Security problems empirically fall into two categories: bugs and flaws. Roughly half of the problems we encounter in the wild are bugs and about half are design flaws. A significant number of the bugs can be found through automated testing tools which frees you up to focus on the more pernicious design issues. Even in the time of AI, there's a discussion to be had.  In addition to detecting the presence of common bugs as we have done with static analysis for years, however, we can also imagine automating the application of corrective refactoring. In this talk, I will discuss using OpenRewrite and the Moderne cli to fix common security issues and keep them from coming back.  

On the one hand, Machine Learning (ML) and AI Systems are just more software and can be treated as such from our development efforts. On the other hand, they behave very differently and our capacity to test, verify, validate, and scale them requires a different set of perspectives and skills. This presentation will walk you through some of these unexpected differences and how to plan for them. No specific background in ML/AI is required, but you are encouraged to be generally aware of these fields. The AI Crash Course would be a good start.

On the one hand, Machine Learning (ML) and AI Systems are just more software and can be treated as such from our development efforts. On the other hand, they behave very differently and our capacity to test, verify, validate, and scale them requires a different set of perspectives and skills. This presentation will walk you through some of these unexpected differences and how to plan for them. No specific background in ML/AI is required, but you are encouraged to be generally aware of these fields. The AI Crash Course would be a good start.