Applied AI: Observability

Information in this post reflects publicly available sources as of October 18, 2026. A customer writes in, angry. Your support assistant told them their refund had been approved. It had not. They want to know why, and so does your manager. You open the logs. They show the request arrived at 14:02, returned HTTP 200, and took 6.8 seconds, and nothing more. You cannot see what the model was asked, which documents it retrieved, which tools it called,… Read More

Applied AI: Fine-Tuning

Information in this post reflects publicly available sources as of October 17, 2026. One team spends three weeks fine-tuning a model on two thousand internal policy documents, so that it will "know" the company's rules. The result writes in exactly the company's tone. It also cites policies that do not exist, mixes up last year's rules with this year's, and needs retraining every time HR updates a page. A retrieval proto… Read More

Applied AI: Cost Control

Information in this post reflects publicly available sources as of October 17, 2026. During the pilot, your support agent cost about $40 a month, and nobody looked at the invoice. Three months after launch, the invoice says $58,000, and finance wants to know why. Nobody can say. The usage dashboard shows a total but not which feature, which customer, or which part of the prompt is spending the money. When the team finally digs in, the answer is mu… Read More

Applied AI: Structured Outputs

Information in this post reflects publicly available sources as of October 17, 2026. Your team builds a pipeline that reads incoming support tickets and asks a model to classify each one: a category, a priority, the customer's email, and a one-line summary. The prompt ends with "Respond in JSON." Your code calls json.loads on the reply and routes the ticket. In testing, it works every time. In production, it works almost every time. … Read More