Look closer.

Applied AI: Messy Input

Information in this post reflects publicly available sources as of November 2, 2026. A support team tests its new assistant against 200 questions written by the product team. It scores 94%. In production, the questions look different. Customers type on phones with their thumbs, switch between English and Spanish mid-sentence, paste text copied out of scanned receipts, and forward CSV exports with columns in whatever order their system produced. Sa… Read More

Applied AI: Documents, Images, and Multimodal Input

Information in this post reflects publicly available sources as of November 1, 2026. An accounts payable team automates invoice processing with a vision model. It reads scanned invoices, extracts the vendor, date, and total, and posts them to the ledger. For three weeks it works beautifully. Then an auditor finds a $7,340 invoice paid as $1,340: a smudged 7 on a faxed scan, read confidently as a 1, and written into perfectly valid JSON. Down the h… Read More

Applied AI: Privacy and Data Governance

Information in this post reflects publicly available sources as of November 1, 2026. It describes common practice, not legal advice. In the spring of 2023, engineers at Samsung pasted internal source code and meeting notes into ChatGPT to get help debugging and summarizing. Within weeks, the company banned generative AI tools on its devices and networks. The story became the standard warning about AI and confidential data, and it shaped a generat… Read More