AI Tools

Is This Agent Production-Ready?

27 checks across permissions, human oversight, logging, limits, rollback, injection safety, and testing. Tick what's already true, and see what's worth closing before this agent handles anything that matters.

Check what's in place

Runs locally in your browser. Nothing you check here is uploaded, saved, or shared; reloading the page starts over.
0 of 27 checked (0%) Every critical item is unchecked.
Ready when you are.

Watch: work through the checklist

No sound. Each step is captioned on screen and also written out in the guide below.

Use it in three steps

  1. 01
    Go through each item

    Check what's genuinely true today, not what's planned.

  2. 02
    Look at what's critical and unchecked

    Those are the gaps worth closing first.

  3. 03
    Share the report

    Copy it into a ticket or a review, with the reasons for what's still open.

What "critical" means here

  • Critical: missing this is how agents cause real damage — unscoped permissions, no kill switch, no undo, treating outside content as instructions.
  • Important: narrows a real risk, but isn't usually how an incident starts on its own.
  • Recommended: good practice, lower stakes if skipped for now.

This can't tell you an agent is safe. It can only tell you what's left unchecked.

Frequently asked questions

Does a 100% score mean the agent is safe?

No. This is a checklist of common gaps, not a certification. It can't see your actual code, and it has no way to catch a risk it doesn't have an item for. Treat a high score as "no obvious gaps from this list," not a guarantee.

Why do some items weigh more than others?

Critical items are the ones that show up again and again in real incidents: unscoped permissions, no way to stop a runaway agent, no rollback, treating outside content as instructions. Missing one of those matters more than missing a "recommended" item.

Where do I check for prompt injection?

The Prompt Injection Scanner checks specific text for injection attempts, and the Agent Security Scanner checks the files that control an agent's permissions and instructions. This checklist is about whether the practice (treating outside content as untrusted) is in place at all.

Is my progress saved?

No, by design: nothing here is saved anywhere, including in your browser. Use "Copy report" or "Download" before you navigate away if you want to keep it.