Archive stories

Guardrails Are More Than Prompt Safety

AI

The nightmare version is easy to imagine. It is 2am. OpsGenie is paging you. A user-uploaded PDF contained instructions the model should have ignored, and now the system has produced an answer that could expose something it should not expose. Maybe that sounds dramatic. But the underlying problem is not exotic. A receipt, invoice, comment, […]

You Do Not Fix Hallucinations With One Prompt

AI

In the previous post, I wrote about deciding which parts of an expense workflow should be automated first. Some decisions are better handled with ordinary code. Some need model judgement. Some should surface information for a reviewer without making the final call. Over time, the goal is to automate more of the workflow as the […]

The Hard Part Was Deciding What to Automate First

AI

The ideal expense workflow is one you barely notice. An expense is captured automatically. The right policy is applied. The supporting evidence is checked. Obvious cases move through without anyone needing to think about them. A person only gets involved when something genuinely needs judgement. I hate spending time submitting expenses. Nobody wants to spend […]

The Prompt Had Too Many Jobs

AI

Prompt engineering is often talked about like it’s magic. Write the right words. Add the right examples. Tell the model to be careful. Tell it to think step by step. Tell it not to hallucinate. Tell it to output JSON. Tell it to be concise. Tell it to be accurate. Tell it to do everything. […]