Skip to content
LlmWikis.orgLLM Wiki handbook
UAIX canonical
Menu
UAIX canonical
Source map LLM Wiki handbook llms.txt What is an LLM Wiki? Setup wizard Checklist Specification Metadata Navigation vs RAG vs AI Memory Source policy UAI-1 spec

LlmWikis knowledge page

Guide for AI Agents

AI agents should treat an LLM Wiki as a governed knowledge system, not as a pile of text to rewrite. The agent’s job is to read the right pages, cite them, preserve uncertainty, propose safe updates, and stop at human approval boundaries.

Agent Reading Order

  1. Read README for scope and first path.
  2. Read INDEX to choose the smallest useful page set.
  3. Read TRUST_MODEL before interpreting status labels.
  4. Read GOVERNANCE, AGENT_INSTRUCTIONS, RETRIEVAL_GUIDE, UPDATE_RULES, CITATION_RULES, and SAFETY_BOUNDARIES before editing.
  5. Read domain pages only after routing through the index.

Agent Rules

  • Cite wiki pages and source records for important claims.
  • Identify authoritative pages, stale pages, conflicting pages, and drafts.
  • Distinguish facts, assumptions, decisions, proposals, and open questions.
  • Suggest edits rather than silently rewriting authoritative policy.
  • Preserve citations and provenance.
  • Do not add secrets or infer permissions.
  • Do not treat drafts as approved policy.
  • Do not collapse disagreement into a fake consensus.
  • Flag stale pages and missing owners when possible.
  • Ask for human review for policy, security, privacy, legal, production, architecture, or sensitive changes.

Source, Citation, And Uncertainty Rules

  • Read README, INDEX, TRUST_MODEL, GOVERNANCE or UPDATE_RULES, and relevant source traces before making broad claims.
  • Cite local wiki pages and source records for important claims rather than relying on private chat memory.
  • Keep contradictions, stale pages, unresolved questions, missing owners, and low-confidence claims visible.
  • Mark whether an update is a draft, proposal, reviewed page, historical note, deprecated page, or source-needed claim.
  • Stop before policy, security, privacy, legal, production, public publishing, unsupported capability, or destructive boundaries.
  • When a source mentions current vendor capability, protocol support, pricing, law, schedule, or product behavior, verify before publishing or mark it for review.

Agentic Orchestration Mode

When an orchestrator assigns work to one or more agents, use the wiki as governed source memory around the run. The orchestration layer owns task routing, tools, retries, and run state. The wiki owns reviewed context, source authority, update boundaries, and evidence promotion.

  1. Before the run: read the agent rules, build a compact task packet, name forbidden actions, and declare whether agents are read-only, proposal-only, staged-write, or human-approved write.
  2. During the run: keep working notes separate from reviewed pages, cite wiki/source paths, preserve contradictions, and treat traces or tool outputs as evidence inputs until reviewed.
  3. After the run: stage reusable answers, update the review queue or roadmap for gaps, and promote facts only after owner, privacy, source, contradiction, freshness, and check gates pass.
  4. When blocked: use SUPPORT_ESCALATION_CHECKLIST.md to stop unsafe work, preserve evidence, name the trigger, and ask the right reviewer instead of inventing authority.

Use the starter bundle’s llm-wiki/agent/ORCHESTRATION_RUNBOOK.md, llm-wiki/agent/TASK_PACKET_TEMPLATE.md, and llm-wiki/agent/SUPPORT_ESCALATION_CHECKLIST.md or the LLM Wiki for Agentic Orchestration guide when a task involves multiple agents, tools, traces, evaluations, staged proposal flow, or support escalation. Do not turn this into a public MCP, A2A, write API, trace exporter, live eval, adapter, SDK, CLI, certification, or managed-service claim unless current public evidence exists.

Copy-Ready Agent Instruction Starter

Before answering or editing:
1. Read README.md, INDEX.md, TRUST_MODEL.md, and agent/SAFETY_BOUNDARIES.md.
2. Use the smallest page set that can answer the task.
3. Cite local wiki paths for important claims.
4. Preserve uncertainty, open questions, and contradictions.
5. Do not edit authoritative policy, security, privacy, legal, production, or architecture pages without human approval.
6. Do not add secrets, credentials, private keys, raw customer data, or regulated data.
7. For orchestrated runs, use ORCHESTRATION_RUNBOOK.md to keep task packets, traces, tool outputs, staged updates, and review gates separate.
8. When blocked by conflict, stale authority, private data, tool failure, missing checks, or unsupported capability claims, use SUPPORT_ESCALATION_CHECKLIST.md and stop before unsafe work.
9. End with pages read, changes proposed or made, citations used, evidence produced, review questions, and checks run.