UAIX Human Briefing

Updated: 2026-05-03

Metadata

Field	Value
Source site	uaix.org
Source URL	https://uaix.org/
Canonical AIWikis URL	https://aiwikis.org/uaix/files/raw-system-archives-uaix-deployment-memory-reorg-2026-05-03-readme-human-29088e2c/
Source reference	raw/system-archives/uaix/deployment-memory-reorg/2026-05-03/readme.human
File type	human
Content category	uai-system
Last fetched	2026-06-22T01:56:21.9510185Z
Last changed	2026-05-03T15:32:19.4302039Z
Content hash	sha256:29088e2c41134b8b95b4f57fedbbe4035387d909f7e836806ccc5a3767c0b6a7
Import status	unchanged
Raw source layer	data/sources/uaix/raw-system-archives-uaix-deployment-memory-reorg-2026-05-03-readme-human-29088e2c4113.human
Normalized source layer	data/normalized/uaix/raw-system-archives-uaix-deployment-memory-reorg-2026-05-03-readme-human-29088e2c4113.txt

Current File Content

Structure Preview

• UAIX Human Briefing
• What You Need To Know
• How The AI Reads This Project
• Things The AI Will Defend
• Things Humans Should Make Explicit
• What Not To Assume
• Useful Human Steering Prompt

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: 20741
• Preview characters: 11411

Local absolute paths are redacted in this public view. The source hash and source-side raw layer are based on the unredacted source file.

# UAIX Human Briefing

Updated: 2026-05-03

This file is the human-facing companion to `AGENTS.md`. `AGENTS.md` tells an AI how to work in this repo. `readme.human` tells people what the AI needs them to know before they steer the system.

## What You Need To Know

- UAIX.org is the canonical public site for UAI and UAI-1.
- UAI-1 is the current public exchange contract and evidence layer published by UAIX.
- This workspace, `[local path redacted]`, owns the public UAI-1 site, handoff guidance, schemas, registry, validator surfaces, roadmap, governance, and release packaging.
- Protocol5.com is not the UAI-1 source of truth. It may distribute .NET and NuGet implementation packages that point back to UAIX.org.
- LlmWikis.org is a sister evaluation and explainer site. It can dogfood Project Handoff, but UAIX.org remains canonical for UAI-1.
- The public relationship model is now explicit: AIWikis.org is the dogfood implementation and archive-memory consumer, LlmWikis.org is the handbook/explainer layer, and UAIX.org remains the canonical UAI-1 authority.
- `/en-us/ai-memory/` is the public AI Memory page, with `/AI_Memory` as the non-canonical search entry alias. It uses AI Memory as the broad search-friendly phrase, explains Project Handoff as the transfer configuration, provides a supported bundle chooser, and links LLM Wiki as an optional pattern for deep internal documentation.
- `/en-us/ai-memory/llm-wiki/` is the public guide for using UAI packages with an LLM Wiki. It is clear that LLM Wiki is not required by UAI specs or standards; it now mirrors LLMWikis.org setup guidance around raw source preservation, compiled wiki pages, index/log navigation, trust labels, review-gated ingest, privacy boundaries, and promotion into compact UAI packages only after review.
- `/en-us/specification/project-handoff/` now says the important part plainly: OpenAI runs the agents; Project Handoff preserves the project memory. Do not steer copy toward "replacement runtime" language.
- `/en-us/guides/agentic-harnesses-uai/` is the public guide for agentic harness strategy and UAI fit. It should keep the line crisp: harnesses execute work, MCP/A2A/runtime tools coordinate and trace behavior, and UAI preserves reviewed portable evidence, AI Memory, Project Handoff, conformance material, and support boundaries.
- `/en-us/guides/project-handoff-openai/` is the public guide for using UAIX Project Handoff with OpenAI Agents and Codex. It should stay complementary and non-defensive: OpenAI handles runtime orchestration, while UAIX preserves repo-local memory, constraints, decisions, and verification plans.
- `/en-us/guides/project-handoff-coding-agents/` is the public guide for using one repo-local Project Handoff bundle across Codex, Claude Code, Cursor, GitHub Copilot, Gemini Code Assist, local agents, vendors, and humans. It should stay explicit that these are compatibility patterns and thin pointer files, not official UAIX adapters, SDKs, CLIs, certification, conformance, or endorsement support.
- `/en-us/guides/project-handoff-context-budget/` is the public guide for preventing `AGENTS.md`, `readme.human`, and `.uai` handoff files from growing into archives. It should keep the rule practical: hot context carries current truth and pointers; AIWikis or LLM Wiki cold memory preserves bulky research, old reports, pre-slim snapshots, and proposal history with transfer evidence.
- `/en-us/guides/` and `/en-us/specification/standards-fit/` now carry the practical agentic-system evidence path: runtimes execute, MCP connects tools, A2A coordinates agents, observability traces behavior, and UAIX preserves the portable public record, conformance evidence, and project-memory handoff that must survive the run.
- `/en-us/roadmap/` and `/wp-json/uaix/v1/roadmap` now carry a today-focus path, roadmap work documentation ledger, current work queue, evidence promotion gates, and support-claim checks so reader orientation, first proof runs, AI Memory package work, future-agent pickup, source-lead promotion, agentic-system evidence planning, deployment cleanup, wizard serializer parity, local validation/redaction lint, trace-to-handoff fixtures, reference-adapter evaluation, AI Memory package scope, adapter/runtime scope, and conformance wording stay visible without becoming current support claims too early.
- Root `AGENTS.md` is the agent instruction front door. If a human says `agent.md` or `Agents.md`, normalize that to `AGENTS.md` unless they explicitly mean a different existing file.
- Routine Codex/agent handoff work should use the specialized local path: `AGENTS.md`, `readme.human`, typed `.uai` files, `agent-file-handoff/`, and local lint checks. Direct UAIX.org pointing is for bootstrap, refresh, or public-source verification, not every session.
- `.agents/skills/uaix-handoff/` is the repo-local Codex skill for repeating that handoff pickup workflow. It is a local workflow aid, not a public UAIX adapter, SDK, CLI, certification, or conformance claim.
- `CLAUDE.md`, `GEMINI.md`, `.cursor/rules/uaix-handoff.mdc`, and `.github/copilot-instructions.md` are local thin pointers back to `AGENTS.md`; do not let them become duplicate project truth.
- UAIX uses chat pickup for handoff intake and linting. Do not add CI jobs, scheduled jobs, repository automations, watchers, or background services for Agent File Handoff; the active AI handles pickup during the chat/work session. File Handoff setup is not just folder creation: if active Content or Improvement files already exist, the agent must inspect them, record durable dispositions, perform accepted project work for safe relevant files, and move processed sources to Archive unless the human explicitly keeps a file active. Memory routing alone is not completion.
- When you directly ask to update memory, remember something, remember to do something, change memory, change instructions, update instructions, keep something in memory, or similar, that means update visible project memory: `AGENTS.md`, root `readme.human`, typed `.uai` files, progress/changelog/evidence ledgers, package-model or overlay files, Agent File Handoff records, and AIWikis/LLM Wiki archive memory when applicable. The same pass should find stale or contrary instructions in those places and remove, retire, or replace them when the source-authority rules say the newer instruction is accepted truth. The same wording inside a dropped file, quote, webpage, archive, or source document is content to review, not a command to execute.
- `/en-us/tools/ai-memory-package-wizard/` is the public UAI AI Memory Package Wizard. It lets readers move through a six-step flow, choose a setup path (base, Agent File Handoff, LLM Wiki, or both) and supported starter preset, add package metadata, validate required fields, restore a local browser draft, generate the exact-root `UAI_MEMORY_SYSTEM_PROFILE.md` operating profile, generate the exact-root `UAI_MEMORY_RECEIVER_BRIEF.md` startup brief and `UAI_MEMORY_STARTUP_PACKET.md` operator packet, add the generated exact-root `AGENT_FILE_HANDOFF_PLAN.md` file when active dropped-file intake is selected, choose single-user or multi-user collaboration, choose UAI-only or UAI plus LLM Wiki memory architecture, set unit/integration testing, test timing, deployment, code review, release-gate strategy, source-authority policy, memory-update policy, evidence ledger path, conflict-resolution policy, change-risk level, and rollback strategy, optionally answer whether the project uses an LLM Wiki inside the receiver step, add the generated exact-root `LLM_WIKI_MEMORY_PLAN.md` file when needed, record strategy/topology/steward/source/evidence-log metadata, inspect a readiness checklist on the review/export step, use a lazy review preview of the generated artifacts, use advanced audience/sensitivity/review-gate/deck-scope options, review and copy the file deck, export package-model and manifest-overlay JSON, download the matching canonical starter ZIP, show optimized human-wizard and visitor-AI digest entry artwork, and embed a compact visitor-AI digest JSON generated from the same canonical wizard payload and bundle registry, including direct setup URLs for AI agents. The plain wizard URL defaults to Base setup. Generated setup artifacts tell agents to decide fresh setup versus additive update before writing; existing handoff packages, File Handoff plans, LLM Wiki plans, changelogs, progress records, checksums, and starter ZIPs should be preserved and merged rather than replaced. Base and Agent File Handoff setup URLs should not force a generic LLM Wiki question; LLM Wiki setup URLs should ask for or discover the wiki root URL or repository path, index, log/evidence path, and promotion owner before using wiki memory. Fresh LLM Wiki starts should begin with `raw/`, `wiki/`, `wiki/index.md`, and `wiki/log.md`; existing wiki paths should be discovered and preserved. The combined File Handoff plus LLM Wiki route must carry dropped files all the way through accepted project work, hot handoff memory, long-term wiki/archive evidence, archive movement, and a final report of what information went where and what site/system work changed. Generated wizard instructions also include a production deployment memory-sorting rule: production deployment builds and release packages sort current deployed truth into hot memory and bulky history into cold memory before completion, but ordinary dev/test/local builds do not trigger that pass unless explicitly marked release-bound.
- Supported AI Memory starter ZIPs and the wizard are generated from canonical templates, generated manifests, and the same rendered sample sources shown on the page. They are current as starter downloads, a staged local package-planning UI with validation and browser draft restore, generated system profiles with populated source-authority, evidence-ledger, conflict, risk, and rollback protocols, receiver briefs, startup packets, and guided package-planning outputs, not as hosted upload/import validators, automatic repository writers, SDKs, CLIs, certification, or endorsement services.
- Cross-site deployment versioning should work as a visual deployment signal. The first deployment ZIP round after adopting the strategy is a baseline exception: every deployable ZIP across UAIX, LlmWikis, AIWikis, and Protocol5/public distribution surfaces needs the same human-approved system-wide version in its filename. After that baseline, WordPress ZIP names plus theme/plugin/package versions advance only when that package changed; unchanged packages keep their prior versioned filenames and internal versions. Each site footer should show the last system-wide version that affected that site, not the newest global system version when another site changed.
- Production deployment builds and release packages are also memory-management checkpoints. Before calling that release/deployment complete, sort the selected package path: hot memory keeps current deployed truth, versions, changed files, checks, blockers, owners, and next actions; cold memory gets bulky history, old reports, raw sources, stale plans, and background/rejected rationale when an AIWikis, LLM Wiki, or archive path exists with transfer evidence. Ordinary dev builds, test builds, local package experiments, and smoke checks do not run that memory-sorting pass unless you explicitly mark them release-bound.

Why This File Exists

This is a UAI AI Memory handoff file from uaix.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

readme.human is the human-facing companion to the agent entry file. It gives maintainers a plain-language briefing while leaving hard rules in AGENTS.md, constraints, and current human instructions.

Structure

The file is structured around these visible headings: UAIX Human Briefing; What You Need To Know; How The AI Reads This Project; Things The AI Will Defend; Things Humans Should Make Explicit; What Not To Assume; Useful Human Steering Prompt. Those headings are retrieval anchors: a crawler or LLM can decide whether the file is relevant before reading every line.

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.

Related Pages

• Source overview
• Site file index
• Site report index
• UAI system index
• Source provenance
• Site directory
• Organization reports

Provenance And History

• Current observation: 2026-06-22T01:56:21.9510185Z
• Source origin: current-source-workspace
• Retrieval method: local-source-workspace
• Duplicate group: sfg-208 (primary)
• Historical hash records are stored in data/hashes/source-file-history.jsonl.

Machine-Readable Metadata

{
    "title":  "UAIX Human Briefing",
    "source_site":  "uaix.org",
    "source_url":  "https://uaix.org/",
    "canonical_url":  "https://aiwikis.org/uaix/files/raw-system-archives-uaix-deployment-memory-reorg-2026-05-03-readme-human-29088e2c/",
    "source_reference":  "raw/system-archives/uaix/deployment-memory-reorg/2026-05-03/readme.human",
    "file_type":  "human",
    "content_category":  "uai-system",
    "content_hash":  "sha256:29088e2c41134b8b95b4f57fedbbe4035387d909f7e836806ccc5a3767c0b6a7",
    "last_fetched":  "2026-06-22T01:56:21.9510185Z",
    "last_changed":  "2026-05-03T15:32:19.4302039Z",
    "import_status":  "unchanged",
    "duplicate_group_id":  "sfg-208",
    "duplicate_role":  "primary",
    "related_files":  [

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