feat: add Guardian Agents to village-case-study.html
- Add Guardian Agents verification as step 6 in governance flow (8 steps, was 7) - Add Guardian Agents featured card in features section - Update deployment facts: 5 governed features (was 4) - Add verification evidence to "What This Demonstrates" - Add Guardian Agents Philosophy paper link to CTA section - Update EN locale to match Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
TheFlow
parent
98d9363d36
commit
8b1527c5d8
2 changed files with 62 additions and 12 deletions
|
|
@ -22,7 +22,7 @@
|
|||
"ai_label": "AI Model:",
|
||||
"ai_value": "Sovereign Llama (QLoRA fine-tuned)",
|
||||
"features_label": "AI Features:",
|
||||
"features_value": "4 governed features live",
|
||||
"features_value": "5 governed features live",
|
||||
"infra_label": "Infrastructure:",
|
||||
"infra_value": "NZ + EU (no US dependency)"
|
||||
}
|
||||
|
|
@ -53,7 +53,7 @@
|
|||
},
|
||||
"flow": {
|
||||
"heading": "How Governance Works in Practice",
|
||||
"intro": "When a member uses any AI feature, the request passes through six governance checks before a response is generated. Each check is independent and can block or modify the request.",
|
||||
"intro": "When a member uses any AI feature, the request passes through seven governance checks before a response reaches them. Each check is independent and can block or modify the request.",
|
||||
"steps": {
|
||||
"1": {
|
||||
"title": "Member request received",
|
||||
|
|
@ -76,12 +76,16 @@
|
|||
"desc": "The sovereign Llama model generates a response using RAG context filtered by the member's permissions. All processing stays on-infrastructure."
|
||||
},
|
||||
"6": {
|
||||
"title": "Guardian Agents verification",
|
||||
"desc": "Every factual claim in the response is checked against source material using embedding cosine similarity — mathematical measurement, not generative checking. Each claim receives a confidence badge visible to the member."
|
||||
},
|
||||
"7": {
|
||||
"title": "Scope verification",
|
||||
"desc": "Is the response appropriate to what was asked? Detects scope creep and blocks responses that exceed the original request."
|
||||
},
|
||||
"7": {
|
||||
"8": {
|
||||
"title": "Delivery with attribution",
|
||||
"desc": "Response delivered to the member with source attribution. Every step is logged for audit."
|
||||
"desc": "Response delivered to the member with confidence badges, source attribution, and full audit trail. Every step is logged."
|
||||
}
|
||||
}
|
||||
},
|
||||
|
|
@ -106,6 +110,13 @@
|
|||
"title": "AI Memory Transparency",
|
||||
"benefit": "Members can see, edit, and delete what the AI \"remembers\" about them. Full audit dashboard shows every AI interaction.",
|
||||
"governance": "Governance: Multi-stakeholder consent required. Persistence decisions classified and auditable. Members control their own data."
|
||||
},
|
||||
"guardian": {
|
||||
"title": "Guardian Agents",
|
||||
"badge": "NEW",
|
||||
"benefit": "Every AI response is verified against source material using embedding cosine similarity — mathematical measurement, not another generative model checking the first. Each factual claim gets a confidence badge (high, medium, low, unverified) visible to the member.",
|
||||
"governance": "Governance: Verification operates in a fundamentally different epistemic domain from the generation layer — avoiding common-mode failure. Moderator corrections feed back into verification thresholds. All tenant-scoped.",
|
||||
"link": "Philosophical foundations →"
|
||||
}
|
||||
},
|
||||
"limitations": {
|
||||
|
|
@ -143,7 +154,8 @@
|
|||
"• Polycentric governance can operate in production without prohibitive overhead",
|
||||
"• Multi-tenant isolation with per-community governance is achievable",
|
||||
"• Governance violations are detectable and auditable",
|
||||
"• The framework learns from failures (documented incident responses)"
|
||||
"• The framework learns from failures (documented incident responses)",
|
||||
"• Verification without common-mode failure is achievable using mathematical similarity rather than generative checking"
|
||||
]
|
||||
},
|
||||
"does_not_support": {
|
||||
|
|
@ -162,6 +174,7 @@
|
|||
"visit_village": "Visit the Village →",
|
||||
"village_ai": "Sovereign Language Model →",
|
||||
"research_paper": "Research Paper →",
|
||||
"guardian_paper": "Guardian Agents Philosophy →",
|
||||
"research_details": "Research Details →"
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -127,7 +127,7 @@
|
|||
</li>
|
||||
<li class="flex items-center">
|
||||
<span class="w-36 font-medium" data-i18n="what_is.facts.features_label">AI Features:</span>
|
||||
<span data-i18n="what_is.facts.features_value">4 governed features live</span>
|
||||
<span data-i18n="what_is.facts.features_value">5 governed features live</span>
|
||||
</li>
|
||||
<li class="flex items-center">
|
||||
<span class="w-36 font-medium" data-i18n="what_is.facts.infra_label">Infrastructure:</span>
|
||||
|
|
@ -207,7 +207,7 @@
|
|||
<section class="mb-16">
|
||||
<h2 class="text-3xl font-bold text-gray-900 mb-6" data-i18n="flow.heading">How Governance Works in Practice</h2>
|
||||
<p class="text-gray-700 mb-4" data-i18n="flow.intro">
|
||||
When a member uses any AI feature, the request passes through six governance checks before a response is generated. Each check is independent and can block or modify the request.
|
||||
When a member uses any AI feature, the request passes through seven governance checks before a response reaches them. Each check is independent and can block or modify the request.
|
||||
</p>
|
||||
|
||||
<div class="bg-white rounded-xl shadow-md p-8">
|
||||
|
|
@ -250,15 +250,22 @@
|
|||
<li class="flex items-start">
|
||||
<div class="flex-shrink-0 w-8 h-8 rounded-full bg-teal-600 text-white flex items-center justify-center font-bold mr-4">6</div>
|
||||
<div>
|
||||
<h4 class="font-semibold text-gray-900" data-i18n="flow.steps.6.title">Scope verification</h4>
|
||||
<p class="text-gray-600" data-i18n="flow.steps.6.desc">Is the response appropriate to what was asked? Detects scope creep and blocks responses that exceed the original request.</p>
|
||||
<h4 class="font-semibold text-gray-900" data-i18n="flow.steps.6.title">Guardian Agents verification</h4>
|
||||
<p class="text-gray-600" data-i18n="flow.steps.6.desc">Every factual claim in the response is checked against source material using embedding cosine similarity — mathematical measurement, not generative checking. Each claim receives a confidence badge visible to the member.</p>
|
||||
</div>
|
||||
</li>
|
||||
<li class="flex items-start">
|
||||
<div class="flex-shrink-0 w-8 h-8 rounded-full bg-emerald-600 text-white flex items-center justify-center font-bold mr-4">7</div>
|
||||
<div class="flex-shrink-0 w-8 h-8 rounded-full bg-teal-600 text-white flex items-center justify-center font-bold mr-4">7</div>
|
||||
<div>
|
||||
<h4 class="font-semibold text-gray-900" data-i18n="flow.steps.7.title">Delivery with attribution</h4>
|
||||
<p class="text-gray-600" data-i18n="flow.steps.7.desc">Response delivered to the member with source attribution. Every step is logged for audit.</p>
|
||||
<h4 class="font-semibold text-gray-900" data-i18n="flow.steps.7.title">Scope verification</h4>
|
||||
<p class="text-gray-600" data-i18n="flow.steps.7.desc">Is the response appropriate to what was asked? Detects scope creep and blocks responses that exceed the original request.</p>
|
||||
</div>
|
||||
</li>
|
||||
<li class="flex items-start">
|
||||
<div class="flex-shrink-0 w-8 h-8 rounded-full bg-emerald-600 text-white flex items-center justify-center font-bold mr-4">8</div>
|
||||
<div>
|
||||
<h4 class="font-semibold text-gray-900" data-i18n="flow.steps.8.title">Delivery with attribution</h4>
|
||||
<p class="text-gray-600" data-i18n="flow.steps.8.desc">Response delivered to the member with confidence badges, source attribution, and full audit trail. Every step is logged.</p>
|
||||
</div>
|
||||
</li>
|
||||
</ol>
|
||||
|
|
@ -342,6 +349,30 @@
|
|||
</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Guardian Agents — featured -->
|
||||
<div class="bg-gradient-to-r from-teal-50 to-emerald-50 rounded-xl p-6 md:p-8 border-2 border-teal-200 mt-6">
|
||||
<div class="flex items-start gap-4">
|
||||
<div class="flex-shrink-0 w-12 h-12 rounded-lg bg-teal-600 flex items-center justify-center">
|
||||
<svg class="w-6 h-6 text-white" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
||||
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M9 12l2 2 4-4m5.618-4.016A11.955 11.955 0 0112 2.944a11.955 11.955 0 01-8.618 3.04A12.02 12.02 0 003 9c0 5.591 3.824 10.29 9 11.622 5.176-1.332 9-6.03 9-11.622 0-1.042-.133-2.052-.382-3.016z"/>
|
||||
</svg>
|
||||
</div>
|
||||
<div>
|
||||
<div class="flex items-center gap-3 mb-2">
|
||||
<h3 class="text-xl font-bold text-gray-900" data-i18n="features.guardian.title">Guardian Agents</h3>
|
||||
<span class="bg-emerald-100 text-emerald-800 text-xs font-semibold px-2 py-0.5 rounded-full" data-i18n="features.guardian.badge">NEW</span>
|
||||
</div>
|
||||
<p class="text-gray-700 mb-3" data-i18n="features.guardian.benefit">
|
||||
Every AI response is verified against source material using embedding cosine similarity — mathematical measurement, not another generative model checking the first. Each factual claim gets a confidence badge (high, medium, low, unverified) visible to the member.
|
||||
</p>
|
||||
<p class="text-sm text-gray-500 mb-3" data-i18n="features.guardian.governance">
|
||||
Governance: Verification operates in a fundamentally different epistemic domain from the generation layer — avoiding common-mode failure. Moderator corrections feed back into verification thresholds. All tenant-scoped.
|
||||
</p>
|
||||
<a href="/blog-post.html?slug=guardian-agents-philosophy-of-ai-accountability" class="text-teal-700 font-semibold hover:text-teal-900 transition text-sm" data-i18n="features.guardian.link">Philosophical foundations →</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<!-- Honest Limitations -->
|
||||
|
|
@ -416,6 +447,7 @@
|
|||
<li data-i18n="demonstrates.supports.items.2">• Multi-tenant isolation with per-community governance is achievable</li>
|
||||
<li data-i18n="demonstrates.supports.items.3">• Governance violations are detectable and auditable</li>
|
||||
<li data-i18n="demonstrates.supports.items.4">• The framework learns from failures (documented incident responses)</li>
|
||||
<li data-i18n="demonstrates.supports.items.5">• Verification without common-mode failure is achievable using mathematical similarity rather than generative checking</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
|
@ -455,6 +487,11 @@
|
|||
data-i18n="cta.research_paper">
|
||||
Research Paper →
|
||||
</a>
|
||||
<a href="/blog-post.html?slug=guardian-agents-philosophy-of-ai-accountability"
|
||||
class="inline-block bg-teal-900 text-white px-8 py-3 rounded-lg font-semibold no-underline border-2 border-teal-400 hover:bg-teal-800 transition"
|
||||
data-i18n="cta.guardian_paper">
|
||||
Guardian Agents Philosophy →
|
||||
</a>
|
||||
<a href="/researcher.html"
|
||||
class="inline-block bg-teal-900 text-white px-8 py-3 rounded-lg font-semibold no-underline border-2 border-teal-400 hover:bg-teal-800 transition"
|
||||
data-i18n="cta.research_details">
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue