How do I know an AI coding agent really fixed something?

My AI coding agent once told me it tested a feature. It didn't work. When I asked, didn't you say you tested it? It said yes, but not the right way.

"I don't trust you. You have to go take screenshots that you used it as a human to prove that."

Why can't I take the agent's word for it?

Three failure patterns I've hit again and again:

1. Fake testing. It says it tested, but it tested something adjacent, or in a way no user would.
2. Local isn't live. My coding agent fixes things on my machine without flagging whether the fix is deployed, and doesn't explain tradeoffs in terms a non-technical operator can use. GitHub showing a merge doesn't prove production updated either.
3. "Good to go" without the downstream proof. I objected once when an assistant called a provider integration good to go without proof the automation it was supposed to trigger actually fired.

What counts as proof?

The rule in my instruction files: don't say something is fixed, done, live, working or verified without evidence appropriate to the task. In practice that means:

• Screenshots of the agent using the feature like a person would
• The live link, opened and checked, not the local preview
• Rendered output for anything visual or written
• Test results where tests exist

The person who built it does a lightweight self-check before showing me anything meaningful. Independent review is based on risk. And I shouldn't be the primary tester of my own software.

How do I know what's live versus local?

I set up a deployment confirmation step, so every change tells me whether it's live or still local. Ask your agent to end every task by saying which one it is, with the link.

Why does the same bug keep coming back?

Because agents fix symptoms. On my survey software, my coding agent found it had made about 14 earlier "fixes" over weeks, each one tuning a single query. The real cause was an undersized database server. A $5 a month upgrade took errors from 229 per 30 minutes to zero, according to the agent's own report.

The remedy I said yes to is a short check before any fix:

Before you fix anything:
1. Name the actual error.
2. Check whether we're hitting a platform limit.
3. Check whether something already solves this.

Should the agent check its own documents, too?

Yes. Why would you not read a document you had created? An agent should re-read and check its own work before handing it over. For bigger outputs, I want a separate reviewer agent in the loop: should an AI reviewer check work before you see it.