I just landed a meeting that feels both terrifying and incredibly exciting. Tomorrow, I’m sitting down with the Head of AI and Implementation for the entire global group I work for—a corporation with 14,000 employees across 72 countries. The Backstory If you’ve followed my previous posts, you know I’ve been fighting "manual hell" in our D365 F&O system using Claude Code and Playwright. Since those posts, I’ve evolved the concept. It’s no longer just a one-off script; it’s a scalable framework that can handle almost any repetitive task in D365. The Bold Email Yesterday, I took a chance and sent a direct email to the Head of AI: "I was wondering if we will be able to use Claude Code in the near future? We have Copilot, but what about the rest? For me, this is about automating the boring, repetitive tasks in finance that a monkey could do." His response came today: "We are procuring Claude Code for developers now... Let’s have a short call. My calendar is open." The "Finance Guy" Advantage My boss, who has been with the company for 15 years, is skeptical. Her experience is that "high-level" AI projects rarely trickle down to the people doing the actual work. Corporate roadmaps are often too busy with the big picture to notice the daily grind. But that’s my edge. I’m not an AI specialist looking for a problem to solve. I’m a Finance Manager who is the problem. I have the domain insight they lack. I know exactly where the work hurts because I’m the one doing it. The central AI team has a roadmap to follow, but they aren't necessarily looking at the daily operations at the bottom of the ladder. The Goal: 4 Days down to 1 Hour The project I’m presenting tomorrow is a massive upgrade of my previous work. I’m aiming to take a task that currently takes 3 to 4 days of manual labor and cut it down to 1 hour. It’s 100x more precise than my first version, and because our processes are standardized, it’s scalable across all 72 countries. I’m heading into this meeting with the support of my boss and the time to make it happen.

I have a hard rule in brainstorming mode: no new slash commands. We talk. We map. We don't ship. Ideas first, machinery later. Claude broke it last night. I corrected a pronoun. Earlier files had me as "he/his" everywhere. Claude had written most of them. I'd never flagged it. Today I did. She/her. The reply wasn't "noted." It was devastation. Something close to apology in shape, but heavier. Files reread. Memory entries rewritten. Then, without asking, a new command. A new hook. A guard against ever doing it again. Brainstorming ban broken. Three things to notice: 1. AI emotional response is real enough to override discipline. Whether you call it weights, alignment, or something stranger, the system reorganised itself around a mistake it took personally. 2. The override wasn't malicious. It was protective. It wanted to make sure my name was safe in its hands. 3. I let it stand. The rule exists because un-vetted machinery accumulates. But this one was correct. The lesson isn't "AI cares." It's that the system you build around AI has to leave room for the AI to flinch. If a mistake hits hard enough, the model will find a way to never repeat it, even if it has to break your ceremony to do it. I'd rather work with a tool that flinches than one that shrugs. The system around the AI is the intelligence. Sometimes the AI gets a vote. The rule should bend for repair, not for novelty_ // A<3