Daniel Walsh distinguishes decision models from generative chat models: they answer bounded questions that software can use, such as selecting a category, estimating a probability or scoring an item on an ordered scale. The tutorial maps these outputs to classification, detection, search, retrieval, ranking and verification.
Daniel Walsh presents four patterns: asking independent questions together, routing uncertain inputs for clarification, combining separate scores with explicit weights and selecting handlers based on user intent. Dependent questions still require later stages, and thresholds need testing against the application's own examples.
Daniel Walsh brings the patterns together in a customer-support workflow that classifies an issue, estimates disruption and urgency, then routes it to an appropriate handler. A generative model can draft the eventual response, while ordinary application code retains permission checks, confirmation rules and control over consequential actions.
Watch on YouTube
