AI Con USA 2025 - AI Application Development

Impostering a bit in the AI-verse? Overwhelmed by daily AI announcements? Unsure you're using AI most effectively? Tiny bit of FOMO? We've got you covered! In this workshop, we'll help you become an AI Power User. Become a boss at your job, whatever your role or industry! We'll show you where AI shines and where you'll want to be careful, plus toss you lots of hands-on practice. In our time together, we'll help you pinpoint YOUR niche, build a custom AI assistant, and develop a comms strategy to show off your new skills. You'll walk out with cutting-edge knowledge, a prompt library...

Although there are several controversies and misunderstandings surrounding AI and machine learning, one thing is apparent — people have quality concerns about the safety, reliability, and trustworthiness of these types of systems. Not only are ML-based systems shrouded in mystery due to their largely black-box nature, they also tend to be unpredictable since they can adapt and learn new things at runtime. Validating ML systems is challenging and requires a cross-section of knowledge, skills, and experience from areas such as mathematics, data science, software engineering, cyber-security,...

This session explores the revolutionary potential of agentic systems—autonomous agents equipped with diverse tools to tackle multifaceted tasks effectively. By integrating tools, agentic workflows enable intelligent, adaptive solutions to complex challenges. Apurva will start with an introduction to agentic systems, highlighting their ability to utilize various tools dynamically to achieve goals with minimal human intervention. Through real-world case studies, she will demonstrate how tools like APIs, databases, and external services are orchestrated within these systems to simulate...

In the era of artificial intelligence, software testing has evolved from a finite phase in development to an ongoing, dynamic process of monitoring. Unlike traditional deterministic systems, AI-driven applications operate probabilistically, introducing variability and uncertainty in outputs even with consistent inputs. This paradigm shift requires a rethinking of testing strategies, moving towards continuous monitoring to ensure performance, fairness, and reliability in production environments. This session will explore how QA teams can integrate AI-specific methods, anomaly detection, and...

Tool calling is more than just a technical detail—it’s the most important piece of how AI agents get things done. It allows agents to connect to systems, access data, and perform tasks effectively. Building good tools is very similar to building good APIs, as they need good design for things like authentication and security. But building good tools requires a bit more than knowledge about building APIs.

In this session, we’ll explore how tool calling works, why it matters, and how to do it right. You’ll learn different ways to build tools that help agents connect to APIs, databases...

The adoption of open-source AI software introduces a new family of vulnerabilities to organizations. Some components in AI, like model serving, include Remote Code Execution (RCE) by design, like when loading pre-trained models from external sources. Traditional SCA and SAST approaches are not built for the AI ecosystem leaving a huge & insecure attack surface. The irony is that in the AI ecosystem, security issues such as remote code execution are actually a feature and not a bug, often specified explicitly in the docs, which most devs don’t read. AI models are often downloaded from...