Tool Gate · How it works
How the Voice Prompt Forge gate works
How the Voice Prompt Forge scores a voice-agent system prompt on 6 craft dimensions to 100: a safety-block gate forces a distinct MISSING GUARDRAILS verdict — outside the score bands — when a non-negotiable safety block is absent, which is how a prompt scoring a perfect 100 on craft still reads MISSING GUARDRAILS because it never says don't confirm before the tool returns.
How the gate works
This tool grades a voice-agent system prompt's craft and its non-negotiable safety blocks. Each control is marked from your own evidence and weighted into a 0–100 score — and then the score is run past a gate that can only make the verdict worse.
The 6 weighted controls
| Signal | Weight |
|---|---|
| Grounded-answer instruction | 22 |
| Scope boundary | 18 |
| Recovery / repair block | 18 |
| Persona / tone consistency | 14 |
| Closing confirmation pattern | 14 |
| Latency-aware brevity | 14 |
| Total | 100 |
The verdict bands
Four safety blocks are checked independently of the craft score: AI-identity disclosure, never confirm before the tool returns, barge-in / interruption yield, and an escalation trigger list. If even one is missing, the verdict is MISSING GUARDRAILS no matter how high the craft score reads - craft never buys its way past a missing guardrail.
In the worked sample it scores 100 out of 100 and still reads MISSING GUARDRAILS — Every craft block is present and full-marked - grounding, scope boundary, recovery, persona, closing confirmation, and latency-aware brevity - for a perfect craft score of 100/100, which would normally read READY TO SHIP. But the prompt never instructs the agent to withhold confirmation until the tool actually returns - the 'never confirm before the tool returns' safety block is missing. That's one of four hard safety gates, and craft can't buy it back: the verdict is MISSING GUARDRAILS. The one thing to fix first: Add the never-confirm-before-the-tool-returns rule - the agent must wait for the tool's actual result before telling the caller it's done..
Common questions
Can something score well on the How the Voice Prompt gate works and still fail?
Yes. The weighted score is run past a worsen-only gate — the Safety-block gate — that can only make the verdict worse. In the worked sample it scores 100 out of 100 and still reads MISSING GUARDRAILS, because every craft block is present and full-marked - grounding, scope boundary, recovery, persona, closing confirmation, and latency-aware brevity - for a perfect craft score of 100/100, which would normally read READY TO SHIP. But the prompt never instructs the agent to withhold confirmation until the tool actually returns - the 'never confirm before the tool returns' safety block is missing. That's one of four hard safety gates, and craft can't buy it back: the verdict is MISSING GUARDRAILS.
What is a worsen-only gate?
A dispositive rule that can only lower a verdict, never raise it. One fatal flaw overrides an otherwise-good score, because a single disqualifying gap shouldn't hide behind a high average. The tool also names the one thing to fix first — here, "Add the never-confirm-before-the-tool-returns rule - the agent must wait for the tool's actual result before telling the caller it's done.".
Lints a prompt's craft and stated safety instructions - it can't verify the deployed voice agent actually obeys them at runtime. Test the live agent before shipping.
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/voice-prompt-forge.html" title="How the Voice Prompt Forge gate works — RedHub AI" width="760" height="1791" 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/voice-prompt-forge">How the Voice Prompt Forge 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/voice-prompt-forge"><img src="https://redhub.ai/visuals/tool/voice-prompt-forge-share.png" alt="Diagram of the Voice Prompt Forge: six craft dimensions scoring 100 and a safety-block gate forcing a distinct MISSING GUARDRAILS verdict on one missing safety block." 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 Voice Prompt Forge works. More diagrams in the Visual Field Guide.