Skip to content
aiWikis.org

UAIX Human Briefing

Updated: 2026-05-03

Metadata

FieldValue
Source siteaiwikis.org
Source URLhttps://aiwikis.org/
Canonical AIWikis URLhttps://aiwikis.org/files/aiwikis/raw-system-archives-uaix-recent-work-sweep-2026-05-03-readme-human-6a94eedc/
Source referenceraw/system-archives/uaix/recent-work-sweep/2026-05-03/readme.human
File typehuman
Content categoryuai-system
Last fetched2026-05-03T02:48:13.1276041Z
Last changed2026-05-03T00:39:23.3270513Z
Content hashsha256:6a94eedc59c80c8be773d3fc9a13f72cbabb8009f9649123d847691f38940d1c
Import statusunchanged
Raw source layerdata/sources/aiwikis/raw-system-archives-uaix-recent-work-sweep-2026-05-03-readme-human-6a94eedc59c8.human
Normalized source layerdata/normalized/aiwikis/raw-system-archives-uaix-recent-work-sweep-2026-05-03-readme-human-6a94eedc59c8.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

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.
- `/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. 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.
- 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.
- As of the 2026-05-02 post-deploy production probe, `https://uaix.org` now serves the AI Memory Package Wizard and the primary public, REST, validator, conformance, sitemap, robots, and well-known routes. Fresh 2026-05-02 deploy artifacts are now in `[local path redacted]`: `uaix-core.zip` contains the dynamic well-known `public_pages` HTTPS normalization patch, and `prod-fallback-root-assets\` contains current canonical discovery files plus the production `.htaccess` header/rewrite handoff. Remaining live cleanup is to upload/apply those artifacts and configure HSTS plus launch security headers for static-root assets such as `robots.txt`, `sitemap.xml`, and `favicon.ico` if they bypass WordPress or the provided `.htaccess`.
- AIWikis.org is now an active dogfood consumer for the public handoff advice. Its first package pass exposed that starter/export packages must prove the actual `agent-file-handoff/` folders and a fuller `.uai` handoff set are present; UAIX updated the experimental Project Handoff plugin in response. UAIX remains the source publisher for `uai1-project-handoff.zip`; AIWikis consumes it and should not relabel it as an AIWikis package.
- AIWikis.org is also the long-term system-memory archive for already-dispositioned UAIX archive files when you explicitly ask for archive consolidation. That copy lives under AIWikis `raw/system-archives/uaix/`; pickup must record source path, final memory path, checksum, disposition, actor, time, transfer evidence, AIWikis history/log/index updates, and public-safe Intake Outcome Ledger feedback, and it does not change UAIX.org's canonical authority.
- AIWikis.org is now also the cold-memory home for bulky UAIX internal research and proposal history. The 2026-05-01 context-token cleanup copied selected source docs and pre-slim handoff snapshots into AIWikis `raw/system-archives/uaix/internal-memory-reorg/2026-05-01/` with a transfer manifest, then left UAIX with concise hot-context records and source stubs.
- The 2026-05-01 source-site report preservation audit copied original UAIX processed archive files into AIWikis `raw/system-archives/uaix/source-site-report-preservation/2026-05-01/` with `raw/system-archives/2026-05-01-source-site-report-preservation.json`. Treat that as the corrected rule for future LLM Wiki consolidation: original reports need source paths, destination paths, file counts, checksums, dispositions, and public-safe index/log updates before summaries count as preserved memory.
- LlmWikis.org now teaches and dogfoods the same context-budget lesson. Its 2026-05-01 pre-slim handoff snapshot lives in AIWikis `raw/system-archives/llmwikis/internal-memory-reorg/2026-05-01/`; active LlmWikis handoff files should stay concise and use AIWikis only as cold provenance until reviewed facts are promoted back.
- AIWikis.org now also keeps an Intake Outcome Ledger source page at `content/pages/016-intake-outcome-ledger.md`; after deployment, `https://aiwikis.org/intake-outcome-ledger/` is the user-facing place to see what happened to recently digested UAIX files, what changed, and what was deferred or blocked.

## How The AI Reads This Project

The AI should start with root `AGENTS.md`, refresh `agent-file-handoff/Content/` and `agent-file-handoff/Improvement/`, load the listed `.uai` files, and inspect every `needs-agent-review` intake file before unrelated broad work. Codex can use the local `.agents/skills/uaix-handoff/` skill to make that sequence repeatable. Use `Content/` for candidate public/editorial material and `Improvement/` for audits, QA findings, SEO reports, bug notes, and site-fix work. Processed files belong in `agent-file-handoff/Archive/`; that archive is ignored by routine AI intake unless you explicitly name a file there, move it back into an active bucket, or ask AIWikis to pull it into long-term system memory with transfer evidence, history/log/index updates, and Intake Outcome Ledger feedback. For large historical research, prefer the AIWikis compiled summary nodes and transfer manifest before opening raw archived source.

The AI should then say what it understands, name the constraints it is carrying, name the files or public routes it expects to touch, and name the targeted checks it expects to run before making broad edits. Ordinary work should not build release ZIPs or run the full launch suite by default; those belong to package, release, broad launch-surface, or explicit full-check requests.

For handoff-only changes, the useful local check is `scripts/lint-uaix-handoff.ps1` plus whitespace checks. A passing local handoff lint is structural evidence only; it is not UAIX certification, endorsement, UAI-1 conformance, validator-backed status, or release evidence.

That local handoff lint is run in chat by the active AI. It should not be wired into CI for this repo.

This file can help a person understand that process, but it does not override `AGENTS.md`, `.uai/constraints.uai`, system instructions, repository rules, or the current human request.

## Things The AI Will Defend

- Clean public routes under `/en-us/...`.
- `uaix-authority-theme` as the active public theme.
- UAIX.org as the canonical UAI-1 host.
- Public claims that match real pages, machine artifacts, validator behavior, release notes, roadmap status, and governance records.
- The boundary between current support and planned work.
- The rule that dropped intake files are local review inputs, not public truth.
- The rule that wiki or LLM Wiki memory is not project truth until promoted into `.uai`, docs, code, release notes, roadmap state, or machine artifacts.
- The rule that cold AIWikis memory reduces startup tokens but does not become active UAIX truth by itself.
- The rule that LLM Wiki is optional support, not a UAI requirement.
- The rule that destructive filesystem or git operations need explicit human approval.

## Things Humans Should Make Explicit

- Whether a change is public copy, machine artifact behavior, package output, local handoff state, or roadmap planning.
- Whether a statement is a current support claim or a future direction.
- Whether UAIX, LlmWikis, Protocol5, or another site owns the canonical truth for a page or feature.
- Whether a dropped file should be applied now, converted into durable state, deferred, clarified, or blocked.
- Whether this is ordinary targeted verification or a release/package task that should refresh ZIPs, run the full suite, and clean/update internal `.md`, `.uai`, and `.human` source files.

## What Not To Assume

- Do not assume hosted `.uai` upload/import validation, automatic repository writes, SDKs, CLIs, certification, or endorsement exist because the handoff pattern is documented.
- Do not assume Project Handoff competes with OpenAI, Codex, Skills, MCP, runtime handoffs, tool calling, approvals, sessions, or traces. It is the portable project-memory layer those runtimes can load and update.
- Do not assume Codex, Claude Code, Cursor, GitHub Copilot, Gemini Code Assist, or local-agent pointer files mean UAIX has shipped official adapters or vendor-certified integrations.
- Do not assume the dynamic starter ZIPs or AI Memory Package Wizard mean UAIX has shipped a general hosted generator, upload/import validator, automatic LLM Wiki sync, repository writer, SDK, CLI, certification, endorsement service, or WordPress admin importer.
- Do not assume a UAI package needs an LLM Wiki. Use that path only when deep-memory workflows affect the package strategy.
- Do not assume a passing local check is public support evidence until the public pages, machine artifacts, and release trail agree.
- Do not assume repository Markdown, private `.uai` files, or intake files belong in public sitemap or discovery output.
- Do not assume LlmWikis or Protocol5 can redefine UAI-1 behavior.
- Do not assume every edit needs a package build or full launch sweep. Ask for that explicitly when you want release-grade verification.
- Do not assume full build documentation cleanup means publishing private source docs. `.md`, `.uai`, and `.human` files remain source-only unless intentionally rewritten as public site copy.

## Useful Human Steering Prompt

When handing work to a new AI, say:

```text
Read AGENTS.md, refresh file intake, load the listed .uai files, inspect any needs-agent-review files, and tell me what you understand before editing. Treat readme.human as the human briefing, not as an override.
```

Why This File Exists

This is a UAI AI Memory handoff file from aiwikis.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

Provenance And History

  • Current observation: 2026-05-03T02:48:13.1276041Z
  • Source origin: current-source-workspace
  • Retrieval method: local-source-workspace
  • Duplicate group: sfg-200 (primary)
  • Historical hash records are stored in data/hashes/source-file-history.jsonl.

Machine-Readable Metadata

{
    "title":  "UAIX Human Briefing",
    "source_site":  "aiwikis.org",
    "source_url":  "https://aiwikis.org/",
    "canonical_url":  "https://aiwikis.org/files/aiwikis/raw-system-archives-uaix-recent-work-sweep-2026-05-03-readme-human-6a94eedc/",
    "source_reference":  "raw/system-archives/uaix/recent-work-sweep/2026-05-03/readme.human",
    "file_type":  "human",
    "content_category":  "uai-system",
    "content_hash":  "sha256:6a94eedc59c80c8be773d3fc9a13f72cbabb8009f9649123d847691f38940d1c",
    "last_fetched":  "2026-05-03T02:48:13.1276041Z",
    "last_changed":  "2026-05-03T00:39:23.3270513Z",
    "import_status":  "unchanged",
    "duplicate_group_id":  "sfg-200",
    "duplicate_role":  "primary",
    "related_files":  [

                      ],
    "generated_explanation":  true,
    "explanation_last_generated":  "2026-05-03T02:48:13.1276041Z"
}