Technical AI Insights

A good evaluation dataset ensures that LLM applications or AI agents behave correctly, safely, and consistently. We walk through the what, why, and how for building your own evaluation dataset for your next AI application, including full samples.

The mortgage industry files public data on origination volume, denial rates, and loan economics. That makes it one of the few industries where you can run a real ROI analysis on AI, not a hypothetical one. In this article, we walk through three ways intelligent document processing generates measurable returns for mortgage originators, using citable benchmarks from the MBA and HDMA.

“What’s the return on investment for this?” It’s one of the most common questions we field, and it’s everywhere in the AI discourse. So how do you unlock real value from AI? How should we be thinking about ROI in a time when hype is everywhere? We unpack three major approaches to building with and thinking about the value created from AI.

One of the best applications for AI agents is tedious and repetitive tasks. We decided to build an agent example agent using our AI Agent Starter Pack to show a concrete example in action. This is an open-source project you can clone and work with to give yourself a head start.

AI Agents have been defined as software entities designed to perceive their environment, make decisions and take actions to achieve specific goals. We dive into the differences between AI Agents and AI Workflows, the components of agents, and critical components and considerations for building an AI agent.