3 posts
By the time a team reaches an advanced AI travel copilot, the hard question is no longer "Which model should we use?" It is "What has to happen, in what order, with what evidence, with what state, and under whose approval before this system can be trusted in production?" That is an architectural ...
Useful AI systems usually fail for ordinary software reasons before they fail for exotic model reasons. A prototype looks impressive when a single prompt produces a plausible answer, but production systems do not consume plausibility. They consume records, decisions, and actions that need to be r...
Most failures in real AI products do not come from the model suddenly becoming unintelligent. They come from asking a model to do work that actually belongs to a larger system: fetch the right data, interpret a messy document, check a schema, track state across steps, and show evidence for the an...