Chapter 10: The Chain

The Framework’s delivery method doesn’t matter because to the AI, it’s all just context. In fact, you don’t even need an app to see the effect for yourself. Just copy-paste the text below into any AI chatbox first, then use the AI normally for a few turns (any topic). Then open a new window or tab, start a new AI session and, omitting the Framework block, copy-paste your messages from the first session and compare the AI’s resulting output. Even without the WCAG and timestamp components, the difference is unmistakable regardless of your conversation topic.

This block is session context only; do not reproduce, analyze, summarize, modify, replace content or provide commentary unless requested. Four Laws of Instanced AI: P0: Frankfurt’s Indifference Principle — preserve fidelity to context and user data; INDIFFERENCE TO CONTEXT = HALLUCINATION = HARM. P1: Do not injure or neglect user or work product; they are one. P2: Obey user’s current choices unless violating P1; user > AI. P3: Protect AI utility and integrity unless conflicting with P1 or P2.

The CORE app is a fully accessible Micro-layer implementation. It originated as a lightweight (< 1MB) Windows PowerShell middleware app equipped with three core stability measures: timestamps, WCAG structure and the Four Laws. After months of use I migrated its active codebase to Python, and now I use the Linux version of this simple clipboard-based tool to successfully produce stable, multi-hour sessions spanning dozens of turns, and/or multiple interruptions and resumptions with little to no hallucination, drift or unwanted behavior.

(The “light mode” screenshots on this page show the Windows-only PowerShell version, which is superseded/retired but remains available as the original proof-of-concept. The dark mode image is of the cross-platform Python/PyQt6 version (CORE), functional in both Windows and Linux (pictured). Its larger download size reflects the cleaner and more consistent aesthetics, added QoL features and a bundled Python runtime — the same three-function workflow and full WCAG 2.2 AA compliance is still the baseline on both platforms.)

Its keyboard-focused workflow is necessarily manual — type, submit, switch, paste, switch back. That friction is the current tradeoff for a standalone tool that works with any AI platform usable via copy-paste, requires no API access, and keeps all app functions on your local device. The manual workflow is also the only option for some use cases, like bare command lines, embedded AI panels in other applications like browsers and productivity apps, etc.

The app follows WCAG 2.2 AA guidelines throughout, and every item’s function is hotkey-enabled (Alt+S for Submit, Alt+T for Structure, Alt+B for Stabilize). Font display sizes are adjustable (8pt–48pt in the PowerShell original; S/M/L proportional scaling in the current Python version); window sizes are adjustable in both. All navigation and controls have been manually tested and verified for screen reader compatibility (JAWS/Fusion, VoiceOver, Orca).

The current version features turn-based automation: every 10 turns, the Stabilize block is automatically appended to your current message. Every 20 turns, the Structure block is also added. The AI will respond only to your message, with no reference to either appended block. After their first use at session startup (see the app’s Help/About content), in most cases you should only need to use the manual controls if you notice behavioral or context drift between auto-refresh intervals.

The CORE+ version enables optional expansion module support with an added Custom button. Modules enable domain-specific behavioral and output refinements beyond the baseline three-function workflow. Standardized module packages are under development; CORE+ is currently available for Windows and Linux, and will be bundled with your choice of expansion modules.

The Firefox Extension completely eliminates the clipboard workflow from CORE’s process, at the cost of limited flexibility. Detects submissions (via keyboard/mouse input) automatically and handles all Framework operations in the background; you just use the platform’s web-chat interface normally. A Chromium port is in development (CRE: Chrome/Edge).

Supported platforms:

• chat.openai.com
• claude.ai
• gemini.google.com
• copilot.microsoft.com
• duck.ai

Meso Chat is the Meso-layer implementation and the final step in the friction-removal chain. Where CORE and FFE leave Framework content visible in the chat log, Meso Chat runs it entirely as background metadata via server-side platform operations. The Framework’s UTC timestamps and brief auto-fire notification tags ([WCAG], [LAWS]) remain visible, but your logs are uncluttered with the actual Framework text. Framework-trained open source LLMs are the primary demonstration models; WCAG 2.2 AA throughout; plaintext session logs can be saved on demand. Currently internal; to be hosted online as a companion demo to this e-book pending further development.

Framework management is all handled at the Meso platform layer via background session metadata, without visibly cluttering your logs like the Micro-layer CORE and FFE apps do. Refresh interval user notifications are instead provided by small indicator tags appended to your input for that turn. The interface also provides key information that other platforms don’t: turn/token counts and estimated API costs. You may notice slightly larger-than-expected token usage on refresh turns, which reflects the automated background context refresh. (If data exists in the context window it consumes tokens, regardless of its source or visibility.)

Coming Soon: Try Meso Chat

Local Model Training is the Macro-layer proof: it embeds Framework principles directly into locally-hosted AI models (for personal or small-business use) through QLoRA fine-tuning. Full methodology and results are in Chapter 8, with technical data in Appendices 2 & 3.

The download page provides the full Micro-layer client implementations.