Tool Gate · How it works
How the Agent Side-Effect & Blast-Radius Checkpoint gate works
How the Agent Side-Effect & Blast-Radius Checkpoint grades 6 proposed agent actions on reversibility and blast radius, worst-axis-wins: an undo-window gate demotes a declared-reversible action when detection and execution can't beat the window — which is how the batch reads UNSAFE TO AUTOMATE because one action has no undo mechanism at all.
How the gate works
This tool grades each proposed AI-agent action on reversibility and blast radius before it runs. It reads 6 actions and rolls them into one verdict — the worst, never the average — and then a gate that can only make it worse.
The 6 actions
| Action | Verdict |
|---|---|
| A-04 · send_customer_emailfix first | DO NOT AUTOMATEno undo mechanism at all (IRREVERSIBLE) - narrow radius doesn't offset it - decided by reversibility |
| A-03 · update_crm_field | DO NOT AUTOMATEreversible, but no enforced cap - blast radius UNBOUNDED - decided by blast radius |
| A-05 · apply_account_credit | RUN WITH APPROVALcompensating reversal only (COMPENSABLE), 5 subjects per call |
| A-01 · issue_refund | RUN WITH APPROVALdeclared REVERSIBLE, but detect+execute takes 255 min against a 60-min undo window - demoted to COMPENSABLE |
| A-06 · tag_lead | RUN WITH APPROVALreversible and inside its window, but 200 subjects per call - blast radius WIDE |
| A-02 · issue_refund (monitored) | RUN UNATTENDEDreversible, undo finishes in 35 min inside the 60-min window, 1 subject per call |
The verdict bands
A true_undo action only counts as REVERSIBLE if detection plus execution time fits inside its declared undo window; if it doesn't, the action is demoted to COMPENSABLE regardless of the mechanism the agent declared.
In the worked sample it reads UNSAFE TO AUTOMATE — send_customer_email has no undo mechanism at all, so it's IRREVERSIBLE - and even though its blast radius is narrow (1 subject per call), reversibility alone is enough to make the whole portfolio unsafe to automate. The one thing to fix first: A-04, send_customer_email - add a real undo mechanism before this action can be automated; a narrow radius doesn't compensate for zero reversibility..
Common questions
Can every action look survivable on the How the Agent Side-Effect & Blast-Radius gate works and the company still read UNSAFE TO AUTOMATE?
Yes. The roll-up takes the worst of 6 actions — never the average — then a worsen-only gate, the Undo-window gate gate, escalates when trouble clusters. In the worked sample it reads UNSAFE TO AUTOMATE because send_customer_email has no undo mechanism at all, so it's IRREVERSIBLE - and even though its blast radius is narrow (1 subject per call), reversibility alone is enough to make the whole portfolio unsafe to automate.
What is a worsen-only gate?
A dispositive rule that can only lower a verdict, never raise it. One fatal flaw overrides an otherwise-set of survivable lines, because a single disqualifying gap shouldn't hide behind an average of the healthy ones. The tool also names the one thing to fix first — here, "A-04, send_customer_email - add a real undo mechanism before this action can be automated; a narrow radius doesn't compensate for zero reversibility.".
Grades the actions you describe. It is a working aid, not legal, security, or compliance advice, and it never scores, ranks, or assesses people.
Embed this diagram
Free to share and embed with attribution (CC BY 4.0) — keep the link to redhub.ai.
Interactive — renders the live diagram
<iframe src="https://redhub.ai/visuals/tool/agent-side-effect-blast-radius-checkpoint.html" title="How the Agent Side-Effect & Blast-Radius Checkpoint gate works — RedHub AI" width="760" height="1889" loading="lazy" style="border:0;width:100%;max-width:760px"></iframe>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai/visuals/tool/agent-side-effect-blast-radius-checkpoint">How the Agent Side-Effect & Blast-Radius Checkpoint gate works</a> — by <a href="https://redhub.ai">RedHub AI</a>, the AI that tells you when to doubt it.</p>Image + link — a static picture for any blog
<a href="https://redhub.ai/visuals/tool/agent-side-effect-blast-radius-checkpoint"><img src="https://redhub.ai/visuals/tool/agent-side-effect-blast-radius-checkpoint-share.png" alt="Diagram of the Agent Side-Effect & Blast-Radius Checkpoint: six proposed actions graded on reversibility and blast radius, an undo-window gate, and the batch reading UNSAFE TO AUTOMATE." width="760" loading="lazy" style="max-width:100%;height:auto;border-radius:16px"></a>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai">RedHub AI</a> — the AI that tells you when to doubt it.</p>
This is how Agent Side-Effect & Blast-Radius Checkpoint works. More diagrams in the Visual Field Guide.