Reference Pages

Publication Warning This page is marked noindex and should not be treated as canonical public authority.

<?php /**

Metadata

Field	Value
Source site	llmwikis.org
Source URL	https://llmwikis.org/
Canonical AIWikis URL	https://aiwikis.org/llmwikis/files/raw-system-archives-llmwikis-recent-work-sweep-2026-05-03-wp-content-the-384dcd5c/
Source reference	`raw/system-archives/llmwikis/recent-work-sweep/2026-05-03/wp-content/themes/llmwikis-knowledge-theme/inc/reference-pages.php`
File type	`php`
Content category	`memory-file`
Last fetched	`2026-06-22T01:56:21.9510185Z`
Last changed	`2026-05-03T02:23:45.2523798Z`
Content hash	`sha256:384dcd5ca4ec980a2c0140fa27c91ef372134e7bf9fed4319cac8f7643a3f27a`
Import status	`unchanged`
Raw source layer	`data/sources/llmwikis/raw-system-archives-llmwikis-recent-work-sweep-2026-05-03-wp-content-themes-llmwikis-knowledge-t-384dcd5ca4ec.php`
Normalized source layer	`data/normalized/llmwikis/raw-system-archives-llmwikis-recent-work-sweep-2026-05-03-wp-content-themes-llmwikis-knowledge-t-384dcd5ca4ec.txt`

Current File Content

Structure Preview

No Markdown headings were detected in this file.

Raw Version

This public page shows a bounded preview of a large source file. The complete source remains in the raw and normalized source layers named in metadata, with the SHA-256 hash above for verification.

Source characters: 38414
Preview characters: 11986

<?php
/**
 * First-class LLM Wiki reference pages.
 *
 * @package LlmWikis_Knowledge_Theme
 */

/**
 * Status block wrapper for registry-backed pages.
 *
 * @param string $type Page type.
 * @param string $source Source summary.
 * @return string
 */
function llmwikis_reference_status( $type, $source = 'LlmWikis public handbook registry and starter templates' ) {
	if ( function_exists( 'llmwikis_status_block' ) ) {
		return llmwikis_status_block(
			array(
				'type'     => $type,
				'authority' => 'Project-owned LLM Wiki standard',
				'status'   => 'Launch-ready reference page',
				'source'   => $source,
				'quality'  => 'Implementation-ready guidance',
				'evidence' => 'Examples, checklists, templates, trust labels, and related routes',
			)
		);
	}

	return '';
}

/**
 * Definitive concept page.
 *
 * @return string
 */
function llmwikis_what_is_definitive_content() {
	$status = llmwikis_reference_status( 'Definitive concept' );
	return <<<HTML
<section class="llmwikis-band"><div class="llmwikis-inner llmwikis-doc-layout"><article>
	{$status}
	<p class="llmwikis-lede">An <strong>LLM Wiki</strong> is a deliberately structured, human-readable, machine-consumable knowledge system designed for both people and AI agents. It preserves durable organizational knowledge, decisions, policies, product context, operating procedures, domain terms, architecture, history, and trusted references in a format that LLMs can safely read, cite, and help maintain.</p>
	<div class="llmwikis-notice"><h2>Not just a wiki an LLM can read</h2><p>A normal wiki might be understandable to a model, but an LLM Wiki is intentionally designed so an agent can answer: what is authoritative, who owns it, when it was reviewed, what is uncertain, which related pages matter, and which actions require human approval.</p></div>
	<h2>Core Definition</h2>
	<table class="llmwikis-table"><thead><tr><th>Property</th><th>What it means in practice</th></tr></thead><tbody>
		<tr><td>Human-readable</td><td>Markdown or equivalent prose that a new teammate can inspect without a special retrieval system.</td></tr>
		<tr><td>Machine-consumable</td><td>Stable paths, metadata, headings, ownership, trust labels, and related links that an agent can parse.</td></tr>
		<tr><td>Durable</td><td>Useful knowledge persists beyond a chat session, ticket thread, or single project handoff.</td></tr>
		<tr><td>Citable</td><td>Important claims point to wiki pages, source summaries, raw evidence, or external canonical sources.</td></tr>
		<tr><td>Reviewable</td><td>Drafts, reviewed pages, stale pages, contradictions, proposals, and deprecated pages look different.</td></tr>
		<tr><td>Permission-aware</td><td>Agents can see what they may read, summarize, propose, edit, or must leave to humans.</td></tr>
	</tbody></table>
	<h2>What A Normal Wiki Often Lacks</h2>
	<p>A traditional wiki is usually optimized for human browsing. It may have stale pages, implicit ownership, weak source trails, uneven headings, duplicated decisions, and pages that sound authoritative even when they are only historical. An LLM Wiki fixes those failure modes by making status, provenance, ownership, uncertainty, and agent permissions first-class.</p>
	<h2>Good Page Test</h2>
	<ul class="llmwikis-checklist">
		<li>The page states its purpose and owner near the top.</li>
		<li>The page includes status, sensitivity, trust level, last reviewed date, and review cycle.</li>
		<li>Facts, assumptions, decisions, proposals, and open questions are separated.</li>
		<li>Related pages are linked intentionally instead of left to search.</li>
		<li>Agent guidance says what an AI may do and what requires approval.</li>
	</ul>
	<h2>Read Next</h2>
	<div class="llmwikis-grid">
		<div class="llmwikis-card"><h3><a href="/why-llm-wikis/">Why LLM Wikis</a></h3><p>Problems solved: context loss, stale docs, unsafe AI use, onboarding drag, and decision amnesia.</p></div>
		<div class="llmwikis-card"><h3><a href="/how-to-build-an-llm-wiki/">How To Build</a></h3><p>A practical implementation sequence from repository choice to review workflows.</p></div>
		<div class="llmwikis-card"><h3><a href="/llm-wiki-vs-ai-memory/">LLM Wiki vs AI Memory</a></h3><p>Durable knowledge base versus portable task context.</p></div>
	</div>
</article><aside>
	<div class="llmwikis-canonical llmwikis-reference"><span>Starter</span><strong>Download the starter bundle</strong><a href="/starter-template/">Open template</a></div>
	<div class="llmwikis-canonical llmwikis-reference"><span>Agent rules</span><strong>For AI Agents</strong><a href="/for-ai-agents/">Open guidance</a></div>
</aside></div></section>
HTML;
}

/**
 * Why page.
 *
 * @return string
 */
function llmwikis_why_llm_wikis_content() {
	$status = llmwikis_reference_status( 'Problem statement' );
	return <<<HTML
<section class="llmwikis-band"><div class="llmwikis-inner">
	{$status}
	<p class="llmwikis-lede">Organizations need LLM Wikis because AI work makes weak knowledge systems fail faster. A model can retrieve stale pages, repeat undocumented assumptions, flatten disagreement, or act on a draft as if it were policy unless the knowledge base carries structure, ownership, freshness, and trust boundaries.</p>
	<h2>Problems Solved</h2>
	<table class="llmwikis-table"><thead><tr><th>Problem</th><th>What goes wrong without an LLM Wiki</th><th>LLM Wiki control</th></tr></thead><tbody>
		<tr><td>Context loss</td><td>Important rationale lives in chat threads, tickets, and people's heads.</td><td>Decision logs, system overviews, runbooks, and reviewed syntheses persist.</td></tr>
		<tr><td>Stale docs</td><td>Old pages look as confident as current pages.</td><td>Last reviewed dates, review cycles, stale labels, and owners make age visible.</td></tr>
		<tr><td>Unsafe AI use</td><td>Agents summarize or edit sensitive material without permission.</td><td>Safety boundaries, sensitivity labels, and update rules define what is off-limits.</td></tr>
		<tr><td>Onboarding drag</td><td>New people and agents cannot tell what to read first.</td><td>README, INDEX, onboarding pages, and retrieval rules create a guided path.</td></tr>
		<tr><td>Decision amnesia</td><td>Rejected options come back because nobody can find the tradeoff record.</td><td>Architecture decisions and decision logs preserve context, alternatives, and consequences.</td></tr>
		<tr><td>Fragmented knowledge</td><td>Docs, tickets, repos, support notes, and policies contradict each other.</td><td>Content types, trust labels, related links, and contradiction records make conflicts explicit.</td></tr>
	</tbody></table>
	<h2>Decision Flow</h2>
	<table class="llmwikis-table"><thead><tr><th>I want to...</th><th>Use</th><th>Why</th></tr></thead><tbody>
		<tr><td>Build a durable internal knowledge base</td><td>LLM Wiki</td><td>It holds long-lived institutional knowledge with ownership, review, and permissions.</td></tr>
		<tr><td>Give an AI agent context for a specific task</td><td>AI Memory</td><td>It packages portable task context without becoming the whole source of truth.</td></tr>
		<tr><td>Transfer a project to another team</td><td>Project Handoff</td><td>It is a focused transfer packet for ownership, constraints, decisions, and checks.</td></tr>
		<tr><td>Improve retrieval over company docs</td><td>LLM Wiki plus RAG</td><td>Curate the source first; retrieve from structured, trusted pages after.</td></tr>
		<tr><td>Onboard a new employee or agent</td><td>LLM Wiki plus curated onboarding memory</td><td>Use the durable wiki as source and export a smaller working path.</td></tr>
	</tbody></table>
	<h2>Common Mistake</h2>
	<div class="llmwikis-verdict"><strong>Bad pattern:</strong> dump every document into a vector database and hope the model figures out authority, freshness, and permissions. <strong>Better pattern:</strong> curate an LLM Wiki with owners, metadata, review cycles, trust labels, and retrieval guidance, then let RAG retrieve from that governed source.</div>
</div></section>
HTML;
}

/**
 * Implementation guide page.
 *
 * @return string
 */
function llmwikis_build_guide_content() {
	$status = llmwikis_reference_status( 'Build guide' );
	return <<<HTML
<section class="llmwikis-band"><div class="llmwikis-inner llmwikis-doc-layout"><article>
	{$status}
	<p class="llmwikis-lede">Build an LLM Wiki in layers: define scope, create the starter structure, add metadata and trust labels, seed the first authoritative pages, establish review workflows, then connect retrieval only after the source is curated.</p>
	<h2>Step-By-Step Build</h2>
	<ol class="llmwikis-steps">
		<li><strong>Choose a home.</strong> Use a private repository, docs-as-code folder, wiki platform with exportable files, or internal documentation system that preserves history and permissions.</li>
		<li><strong>Create the starter structure.</strong> Start with README, INDEX, GOVERNANCE, TRUST_MODEL, CONTRIBUTING, CHANGELOG, organization, architecture, operations, decisions, policies, agent, and onboarding folders.</li>
		<li><strong>Define metadata.</strong> Require title, owner, status, trust level, last reviewed date, review cycle, audience, sensitivity, agent use, and human-review rules.</li>
		<li><strong>Assign owners.</strong> Every authoritative page needs an accountable owner before agents or humans rely on it.</li>
		<li><strong>Create the trust model.</strong> Define authoritative, working-draft, historical, deprecated, proposal, external-reference, and needs-review labels.</li>
		<li><strong>Add the first core pages.</strong> System overview, glossary, decision log, open questions, runbooks, AI usage policy, agent instructions, retrieval guide, update rules, citation rules, and safety boundaries.</li>
		<li><strong>Add contribution rules.</strong> State how humans and agents propose changes, how review works, and what cannot be added.</li>
		<li><strong>Add redaction rules.</strong> Keep secrets, raw customer data, regulated data, private keys, and sensitive strategy out unless explicit governance and access controls exist.</li>
		<li><strong>Add linting.</strong> Check broken links, stale review dates, missing owners, missing metadata, duplicate pages, unresolved contradictions, and uncited claims.</li>
		<li><strong>Add retrieval systems last.</strong> RAG, search, graph APIs, and agent tools should consume the curated wiki, not replace governance.</li>
	</ol>
	<h2>First Week Plan</h2>
	<table class="llmwikis-table"><thead><tr><th>Day</th><th>Outcome</th><th>Done means</th></tr></thead><tbody>
		<tr><td>1</td><td>Scope and skeleton</td><td>Starter bundle installed; README and INDEX drafted.</td></tr>
		<tr><td>2</td><td>Governance and trust</td><td>Owners, trust labels, sensitivity labels, and approval rules named.</td></tr>
		<tr><td>3</td><td>Core knowledge</td><td>System overview, glossary, decision log, and open questions seeded.</td></tr>
		<tr><td>4</td><td>Operations</td><td>Runbooks, release/support process, incident-update rule, and escalation path added.</td></tr>
		<tr><td>5</td><td>Agent readiness</td><td>Agent instructions, retrieval guide, update rules, citations, and safety boundaries reviewed.</td></tr>
	</tbody></table>
	<h2>Implementation Warning</h2>
	<p>Do not wait for perfect tooling. A small, reviewed folder with clear metadata beats a large unowned knowledge platform. The mature system can later add search, embeddings, graph storage, exports, and AI Memory bundles.</p>
</article><aside>
	<div class="llmwikis-canonical llmwikis-reference"><span>Template</span><strong>Starter Template</strong><a href="/starter-template/">Open templates</a></div>
	<div class="llmwikis-canonical llmwikis-reference"><span>Checklist</span><strong>Implementation Checklist</strong><a href="/checklist/">Open checklist</a></div>
</aside></div></section>
HTML;
}

/**
 * Structure page.
 *
 * @return string
 */
function llmwikis_structure_standard_content() {
	$status = llmwikis_reference_status( 'Structure standard' );

Why This File Exists

This is a memory-system evidence file from llmwikis.org. It is shown here because AIWikis.org is demonstrating the real source files that make the UAIX / LLM Wiki memory system work, not only summarizing those systems after the fact.

Role

This file is memory-system evidence. It records source history, archive transfer, intake disposition, or another piece of provenance that should be retrievable without becoming an unsupported public claim.

Structure

The file has no Markdown headings, so its path, frontmatter, file type, and provenance metadata carry most of the retrieval meaning.

Prompt-Size And Retrieval Benefit

Keeping this material in a separate file reduces prompt pressure because an agent can load this exact unit only when its role, source site, category, or hash is relevant. The surrounding index pages point to it, while this page preserves the full content for audit and exact recall.

How To Use It

Humans should read the metadata first, then inspect the raw content when they need exact wording or provenance.
LLMs and agents should use the source site, category, hash, headings, and related files to decide whether this file belongs in the active prompt.
Crawlers should treat the AIWikis page as transparent evidence and follow the source URL/source reference for authority boundaries.
Future maintainers should regenerate this page whenever the source hash changes, then review the explanation if the role or structure changed.

Update Requirements

When this source file changes, update the raw source layer, normalized source layer, hash history, this rendered page, generated explanation, source-file inventory, changed-files report, and any source-section index that links to it.

Provenance And History

Current observation: 2026-06-22T01:56:21.9510185Z
Source origin: current-source-workspace
Retrieval method: local-source-workspace
Duplicate group: sfg-280 (primary)
Historical hash records are stored in data/hashes/source-file-history.jsonl.

Machine-Readable Metadata

{
    "title":  "Reference Pages",
    "source_site":  "llmwikis.org",
    "source_url":  "https://llmwikis.org/",
    "canonical_url":  "https://aiwikis.org/llmwikis/files/raw-system-archives-llmwikis-recent-work-sweep-2026-05-03-wp-content-the-384dcd5c/",
    "source_reference":  "raw/system-archives/llmwikis/recent-work-sweep/2026-05-03/wp-content/themes/llmwikis-knowledge-theme/inc/reference-pages.php",
    "file_type":  "php",
    "content_category":  "memory-file",
    "content_hash":  "sha256:384dcd5ca4ec980a2c0140fa27c91ef372134e7bf9fed4319cac8f7643a3f27a",
    "last_fetched":  "2026-06-22T01:56:21.9510185Z",
    "last_changed":  "2026-05-03T02:23:45.2523798Z",
    "import_status":  "unchanged",
    "duplicate_group_id":  "sfg-280",
    "duplicate_role":  "primary",
    "related_files":  [

                      ],
    "generated_explanation":  true,
    "explanation_last_generated":  "2026-06-22T01:56:21.9510185Z"
}

Next Useful Routes

Start Here A task-first reading path for AIWikis.org, separating newcomer learning, source-memory lookup, maintainer workflow, and AI-agent retrieval.
Topic Index A tag-oriented index for LLM Wiki, AI memory, UAI, source governance, crawling, and retrieval topics.
Source Map AIWikis source-governed page for durable AI memory, evidence routing, and agent-readable retrieval.
LLMWikis.org LLMWikis.org source-system overview for transparent AIWikis memory demonstration.
LLMWikis.org Source Memory Guide AIWikis source-governed page for durable AI memory, evidence routing, and agent-readable retrieval.
LLMWikis.org Files Site-scoped current-source file index for LLMWikis.org.