Mannat·AI·Labs
← Selected work

Case study · 03 · Explainable AI

Mizaan

A multi-agent scoring engine built on one non-negotiable rule: every score the system produces must be explainable to a human.

Status
Live · Zenodo preprint published
Domain
AI evaluation & scoring
Links
mizaan.mannatai.comGitHubPreprint (DOI)

The problem

Organizations increasingly let AI systems score things that matter — sales calls, support interactions, student work, engineering output. Most of these systems are black boxes: a number comes out, and nobody can say why. That is unacceptable anywhere a score affects a person. If you cannot explain a score, you cannot appeal it, audit it, or improve it — you can only obey it.

The approach: a three-layer pipeline

Mizaan is Arabic and Urdu for balance — the scale of justice. The system is designed so that no single model's judgment is ever the final word:

That feedback loop is powered by retrieval-augmented learning: validated decisions become reference material the scoring agents consult on future cases, so the system's judgment converges toward its human overseers' — visibly, case by case, instead of through opaque retraining.

Where it applies

The pipeline is domain-agnostic. It has been designed to work across sales, support, education, operations, and engineering — anywhere performance is scored and the score has consequences.

The research behind Mizaan is published as a sole-authored preprint — When Disagreement Means Learning (or Bias): Human-Governed Memory Consolidation and Counterfactual Diagnosis in Multi-Agent LLM Scoring (Zenodo, June 2026, CC-BY-4.0). doi:10.5281/zenodo.21025602 · code at github.com/JawedCIA/mizaan-eval.

Status

Live at mizaan.mannatai.com and in active development, evaluated across two contrasting domains over three independent runs for the published study. Current focus: hardening the auditor layer and expanding the evaluation criteria library across domains.