Does myAibd provide an AI assistant?

No. The demo does not call an AI model; it provides discovery, comparison, and local workspace examples.

Will my project draft be submitted?

No. Drafts and validation stay in the demo and are not sent to a reviewer.

What mathematical model and units does myAibd use?

myAibd applies Capability Readiness Rubric R = (Task_Fit + Verification_Ease + Privacy_Safety + Cost_Predictability) / 4. Units: Rubric dimensions scored on 1–5 integer scale; prompt/workflow drafts stored locally in browser JSON.

What are the operational boundaries and limitations of myAibd?

Synthetic AI learning and tool-discovery catalogue with local drafts. No live model calls, AI assistant or continuously verified tools catalogue. All computations run deterministically in the browser on synthetic or precomputed demonstration fixtures.

TECHNICAL METHODOLOGY & VERIFICATION SPECIFICATION

myAibd: Mathematical Model, Units & Reproducible Benchmarks

Q: How can I reproduce the benchmark results in myAibd?

Open the interactive browser workspace at ./run/, select Case 1 to inspect the worked result (AI Workflow Evaluation Example: Evaluating a bilingual research-summarization workflow against the 4-factor verification rubric checks whether claims require primary-source citation, whether sensitive data is excluded, and how hallucination risk is mitigated—all executed locally without calling any live LLM API.), and export the JSON or CSV evidence ledger.

Role & Domain Intent: AI learning and discovery demo (Synthetic catalogue and local drafts; no live AI assistant or model calls.)

1. GOVERNING FORMULATION

Equations, Variables & Dimensional Rules

Synthetic AI learning and tool-discovery catalogue with local drafts.

Capability Readiness Rubric R = (Task_Fit + Verification_Ease + Privacy_Safety + Cost_Predictability) / 4

Declared Units: Rubric dimensions scored on 1–5 integer scale; prompt/workflow drafts stored locally in browser JSON.

2. REPRODUCIBLE WORKED EXAMPLE

Step-by-Step Numerical Verification

AI Workflow Evaluation Example: Evaluating a bilingual research-summarization workflow against the 4-factor verification rubric checks whether claims require primary-source citation, whether sensitive data is excluded, and how hallucination risk is mitigated—all executed locally without calling any live LLM API.

Verified benchmark cases from the myAibd browser edition
Component	Execution Mode	Data Source	Live AI / API Calls
Tool Discovery Catalogue	Static client-side filter	Curated synthetic/dated reference entries	Zero live API calls
Evaluation Rubric	Interactive 4-axis checklist	User-scored verification criteria	Deterministic browser math
Prompt & Note Drafts	Local workspace editor	Browser localStorage + JSON export	100% offline / client-side

3. DATA PROVENANCE & OPERATIONAL BOUNDARIES

Validation Status, Scope Exclusions & Disclaimers

Data Status: Synthetic / precomputed browser demonstration fixtures generated deterministically from the project engine.
Operational Limitation: No live model calls, AI assistant or continuously verified tools catalogue.
Client-Side Execution: All interactive views, filters, and JSON/CSV exports execute locally in the user's browser with zero external API calls, zero telemetry, and no server-side persistence.
Author & Principal Investigator: Mohammad Rezwan Khan, PhD (Aalborg University · BESS QA/QC & Power Systems Specialist).