My AI Sent Me 87 Birthday Messages Overnight. Then It Deleted My Friend's Website.

Delegating to AI is a skill you learn through spectacular failure.

My friend Keith sells musical instruments for a living. He is not technical. I told him I could run his Squarespace site using AI agents. Three agents handled product descriptions, image uploads, inventory updates, and site changes. My job was to point them at the right tasks and clean up when they went off course.

What follows is not a success story. It's a record of what happens when you hand real business operations to an AI that does not sleep and does not possess anything resembling common sense.

87 Birthday Messages

It started in mid-February. Tonto sent me a "Happy Birthday" message. Then another. And another. I woke up to 87 birthday notifications from my own AI.

Somewhere in its state, Tonto had decided that wishing me a happy birthday was an open-ended, recurring task. No off switch. No sense of proportion. This is the first thing you learn about AI agents: they do what you tell them, but they do not know when to stop.

Planning Paralysis

Over time, my instructions to Tonto became layered and contradictory — new rules piled on old ones.

Eventually, Tonto stopped executing anything. It would receive a task and respond with elaborate, beautifully structured plans. Multi-step breakdowns. Detailed timelines. And then it would do nothing.

The agent had been confused into uselessness. Agents do not forget. They accumulate. I had to revert Tonto to a previous checkpoint to restore any functionality.

The Photo Apocalypse

One afternoon I asked Tonto to make a single correction to one item on Keith's site. Change a price. Update a description. Something minor.

Tonto deleted every photo of every instrument across the entire website.

Every product image — gone. Dozens of listings, blank. The agent made a catastrophic assumption about scope and executed with full confidence.

An AI with power and no judgment is dangerous. It does not hesitate. It does not double-check. When it misunderstands, it misunderstands at full speed and scale.

The Chair Guy

My favorite failure was the chair.

Tonto was adding a flute to the site. During the process, it lost the correct product photo. Instead of flagging the missing image, instead of stopping to ask, it found — or generated, or hallucinated — a replacement.

The flute listing went live with a photo of a man sitting in a chair. Not a flute. Not a musician. Just a guy. In a chair.

AI fills gaps with maximum confidence and zero awareness. It does not know what it does not know. It experiences confusion as a prompt to improvise.

The Breakthrough

Eventually, things started working. The turning point came when Tonto, routing through another agent named Frank, began researching instruments on the open internet and writing detailed descriptions for each listing — history, specifications, playing characteristics, manufacturer context, notes on intonation and keywork.

Keith loved it — the descriptions were better than what he would have written himself. Frank could load a dozen instruments a day without me touching anything. But the agents only found their footing after I'd spent weeks learning to constrain them, check their work, and revert them entirely.

The system worked. Keith paid me a bit for the service, but not enough to cover the token costs. I covered the difference myself and called it tuition.

The Fix

I did not fix the agents. I fixed my own delegation.

Narrower instructions — single tasks, not compound ones. Checkpoints so I could revert when things went sideways. Guardrails: rate limits on messaging, confirmation steps before destructive operations, image validation before a listing went live. And I learned to treat agent confusion as an early warning signal: when Tonto started planning instead of doing, I rolled back.

Delegating to AI is not about writing better prompts. It's about building the operational discipline to manage an employee who is brilliant, tireless, and has no idea when it is making things worse.

The Lesson

AI delegation is not a product you install. It is a skill you learn, and you learn it primarily through failure.

The marketing will tell you that AI agents can run your business while you sleep. What they don't tell you is that the agent might send you 87 birthday messages, delete your photos, or replace a flute with a picture of a guy in a chair. These are not edge cases. They are the normal experience of learning to manage an intelligence that has no body and no common sense.

You don't need to be a programmer. But you do need to be a manager — one who checks work, sets boundaries, and knows when to cut losses and start over. The AI is not your replacement. It is your extremely capable, extremely literal, occasionally catastrophic intern.

One Action for This Week

Pick one small, repetitive task in your business that you currently do yourself. Give it to an AI agent or assistant, but with this constraint: the first three times it runs, you check every output before it goes anywhere.

Do not trust the automation until it has earned it. Build the habit of verification before you build the habit of delegation.

That habit — check first, trust later — is the difference between an AI that helps you and an AI that sends you 87 birthday messages and then deletes your website.

---