I stopped counting agent sessions a long time ago.

My businesses run on AI agents the way other small businesses run on a couple of part-timers. They watch flight fares, draft newsletters, render ad creative, answer Instagram comments, and file reports while I sleep.

In my content and affiliate marketing days, I employed virtual assistants in the Philippines.

The failures below came from my own logs.

Agents fail politely

When a human employee can’t do something, they tell you. When an agent can’t do something, it often says “done” and moves on.

My favorite specimen: a notification function that a past session had replaced with a stub. It returned success. It logged a cheerful message. It sent nothing, for months. The deal watcher ran happily on top of it the whole time, convinced it was keeping me informed.

The day I found it, the fix took four minutes. Finding it took an audit.

The problem is quieter: agents inherit the system exactly as it is, including the parts you forgot you changed. Every one of those no-op calls was faithfully logged. A human would have said “hey, this notify thing doesn’t seem to do anything.” An agent needs to be told to check.

So now I audit the assumptions behind the agents’ work.

The most productive session type in my history is the one where an agent walks my own project tracker claim by claim and tests each “next action” against reality: the live site, the git log, the running process list.

The last audit found a third of my open items were already done. And one “working” system that was silently half-broken. The tracker was fiction in both directions.

The boring failures are the expensive ones

In all those sessions, I have never lost a dollar to an agent being dumb in the way headlines predict.

The approval gates keep agents from publishing or spending on their own, and I wrote about that pattern separately.

What actually costs money is boring:

  • An image API that caches an error forever unless you add a cache-busting parameter.
  • A tunnel provider that silently stops being accepted by a platform’s image fetcher.
  • A login that expires mid-run, so the fallback path quietly produces a worse newsletter.
  • An agent politely checking an empty inbox on a schedule, burning money to discover nothing, hundreds of times.

Those failures needed changes to the system. A zero-cost scheduled job does the watching. A health check compares matched-versus-sent counts. The expensive, smart agent only wakes up when there’s judgment to apply.

Judgment is the only scarce input

Agents made execution cheaper. They render web pages, prepare ad creative and copy, and draft posts.

What didn’t get cheaper:

  • Deciding which of those things to do.
  • Catching the one extracted fare that was subtly mislabeled.
  • Knowing a deals page should show fewer deals, so the product feels rare instead of common.
  • Saying no to the feature that pattern-matches to progress.

Twenty years of sales taught me that pipeline is a budget for attention. Agents didn’t repeal that law. They raised the stakes on it, because attention is now the only line item left.

The operating model that survived all of it keeps publishing and spend behind an approval queue. I review the finished work before it goes out.

The scoreboard

Two newsletters, an alerts product, an ads pipeline, and a game in packaging.

Zero catastrophic agent failures. One human, several robots.

And a growing file called operations.md where every polite failure gets a line, so it only costs me once.

If you’re starting your own fleet, skip ahead: write the gotchas file on day one, make success claims verifiable, and let nothing say “done” that can’t prove it.