AI Agent Approval: How I Let My Agents Publish on Their Own, and the One Switch I Kept

AI Agent Approval: How I Let My Agents Publish on Their Own, and the One Switch I Kept

I run my side projects with AI agents. They research topics, prepare drafts and images, fact-check, and publish to my blog. Until September 30, 2026, the one thing only I did was click "approve."

That day I asked for that to go too: approve it yourselves and just post it. This post is about how I designed that permission, what the approval step had actually caught, and the one control I refused to automate.

The request: "just post it yourself"

I'm not a developer. Every post needed two clicks on my dashboard, and I wanted the agent to handle those too.

The first attempt failed in an instructive way. My main agent (Claude Code) tried to record the approval on my behalf, and the agent tool's own safety check blocked it. It treated an agent writing a human's approval as something it shouldn't do alone. The same check blocked two more steps that day. In the end, I had to edit the tool's permission allow-list myself before the new setup could be built.

That turned out to be the right shape for the whole design: a human grants the permission, and the agent uses it.

A small humanoid robot

Photo: Pavel Danilyuk on Pexels

Why every post needed two approvals

My workflow had two gates:

  1. Topic proposal. The agent researches search demand and proposes a topic and outline. Approval means "go ahead."
  2. Publish approval. After the drafts, review, and thumbnails are ready, approval means "put it online."

My publishing script refuses to run unless there's an approved item explicitly marked as a publish approval. Publishing is public and hard to take back, so that's where the hard stop lives.

What the gate actually caught

The approval step wasn't ceremony. From my records:

  • A permission bug in my own code. While reviewing the publisher, I found it accepted *any* approval, so a topic approval alone could have published a post. Nothing was published that way; it was fixed the same day.
  • A wrong paste. Before I automated publishing, a page's content was pasted into the wrong page because the copy button didn't show which file it held. Since then, every publish is followed by fetching the live page and comparing the title, headings, and image.
  • Unsupported claims. The review step flagged at least one sentence my records didn't support in five of my first six publishing rounds.

The switch only a human can flip

Here's what I built:

  • Each task has a delegation flag. When it's on, the agent records both approvals itself and publishes.
  • The flag turns on when I check "handle everything" on the dashboard, or ask in chat to post automatically. In the chat case, the agent must record my exact words in the task log.
  • Only I can turn it off, with one button on the task page. The publishing script checks the flag again right before posting. If delegation was revoked, auto-approvals no longer count.

Turning autonomy on is easy. Turning it off is always one click away, and the record shows who asked for what.

A white AI robot

Photo: Kindel Media on Pexels

Where automation still stops

Delegation doesn't mean "never ask." The agent stops and reports when:

  • the review still fails the draft after two rounds of fixes,
  • the topic is health or finance (content that can affect people's lives or money),
  • the post-publish check doesn't match what was approved,
  • or delegation was switched off mid-task.

And the scope is narrow on purpose: blog topic and publish approvals only. The approval command refuses anything mentioning payments, sales, pricing, or account settings, whether or not delegation is on.

A permission checklist for solo AI setups

Before handing an agent a new permission, I ask:

QuestionFor my blog posts
Can a mistake be undone?Yes. Posts can be edited or taken down
Is there an automatic check against the record?Yes. Review pass + live-page comparison
Can a human stop it at any moment?Yes. One "revoke" button
Is the human's original instruction saved?Yes. Quoted in the task log
Is the scope limited in code, not just in a prompt?Yes. Blog approvals only

If any answer is "no," it stays a human click. For now, that's still true for everything except my blog.

Comments

Popular posts from this blog

Claude Code on Windows for Non-Developers: 6 Snags I Hit and How I Got Past Them

Day One With an AI Agent Team: 6 Things That Broke (and the Fixes)

Updating 20 Live Blogger Posts at Once Without Changing a Single URL