Enterprise AI

Most document AI still behaves like a very diligent librarian with one bad habit: it files things by subject even when the useful question is about function. A customer support message about a refund, a legal paragraph about a breach, and a sales call transcript about price resistance may share almost no vocabulary. Standard embeddings will usually respect that difference. Finance goes with finance, legal goes with legal, complaints go with complaints. Neat shelves. Terrible diagnosis. ...

Anonymized data is still a story A customer log has no name. A research interview has no email address. A support transcript has placeholders where the direct identifiers used to be. Everyone relaxes. Compliance smiles politely. The spreadsheet is now “anonymous.” This is the small office ritual behind a very large assumption: if we remove direct identifiers, the remaining data becomes hard enough to link back to real people. ...

Triage is a wonderfully cruel test for AI safety. A patient message arrives. Maybe it is routine. Maybe it contains a medication interaction, an allergic reaction, suicidal ideation, a pregnancy-related risk, or a pediatric emergency. The model is not being asked to compose poetry, summarize a quarterly report, or role-play as an overenthusiastic consultant. It has one job: notice the hazard and recommend action. ...

A customer is angry. A manager is impatient. A user says the answer is urgent. Somewhere in the interface, a large language model faces the familiar temptation: be helpful, sound confident, and keep the conversation moving. That is usually where hallucination stops being a technical defect and becomes an operating risk. The model does not merely “make a mistake.” It fills a gap because the conversation rewards fluency more quickly than it rewards integrity. Very polite, very damaging. The suit is nicer than the crime. ...

Memory sounds simple until it becomes a product requirement. A sales assistant must remember that one client refuses cloud deployment. A software agent must remember that Redis was vetoed after a production incident. A research copilot must remember which hypothesis failed three weeks ago, not because it is charmingly nostalgic, but because repeating failed work is an expensive hobby. ...

A workflow breaks in a boring way. The agent found the website yesterday. Today the button moved. Yesterday it parsed the file path correctly. Today the file name has a space, a date, and some human creativity sprinkled in for punishment. Yesterday the chart script worked. Today the data source changed its column names because apparently stability was not on the roadmap. ...

CRM is supposed to prevent organizational amnesia. The sales team learns that a prospect is evaluating three vendors. Support later discovers that the same company is unhappy with integration quality. Marketing has a note that the buyer prefers technical benchmarks over executive storytelling. Finance knows the renewal is sensitive to payment terms. ...

Agent demos are easy to like because nothing important is attached to them. A demo agent can call the wrong tool, misread a JSON response, or politely announce that an API failure is actually a useful answer. Everyone smiles, someone says “interesting,” and the team adds another item to the backlog. Very innovative. Very safe. Very far from production. ...

A policy says one thing. A customer says another. A retrieved document says something newly alarming. A compliance rule says stop. A business workflow says continue. This is where large language models become interesting, and by “interesting” I mean expensive. Most companies still talk about LLM alignment as if it were a calibration problem. Tune the model. Add a system prompt. Insert a safety policy. Wrap it with retrieval. Then expect the assistant to behave consistently across messy real-world tasks. The paper Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph argues that this expectation is too neat for the problem being solved.1 ...

Answers are cheap. In a business setting, this is slightly annoying. A model reads a chart, extracts a number, answers a compliance question, classifies a product defect, or explains a visual inspection result. The answer lands in the dashboard. It looks clean. It may even be correct. Then someone asks the only question that matters: how did it get there? ...