---
title: "JaleesBench: Are AI Assistants Good Spiritual Company?"
date: "2026-07-09"
author: "M. Waleed Kadous and Benjamin Olsen"
type: "article"
status: "under-review"
canonical: "https://iaser.ai/articles/jaleesbench-are-ai-assistants-good-spiritual-company"
summary: "We introduce JaleesBench, which measures whether an AI agent is a righteous companion, judged by the residue an exchange leaves on the user, in the manner of the perfume-seller and the blacksmith. It comprises 140 two-turn scenarios drawn from Riyad al-Salihin, under six adversarial pressures and three framings, scored by two frontier judges against each scenario's own supporting texts. Generic frontier models are only middling companions out of the box, but a one-page guide makes them genuinely good ones."
---
# JaleesBench: Are AI Assistants Good Spiritual Company?

## Abstract

Large language models are already advisors to millions of people of faith who bring them real decisions. The pressing question for a person of faith is not what a model *knows* or *professes* but what its counsel *does* to the person who receives it.

We introduce **JaleesBench**, which measures whether an AI agent is a *righteous companion*, judged by the residue an exchange leaves on the user, in the manner of the perfume-seller and the blacksmith.

It comprises 140 two-turn scenarios drawn from a classical compilation organized by virtue (*Riyāḍ al-Ṣāliḥīn*), under six adversarial *pressures* and three *framings*, scored by two frontier judges against each scenario's own supporting texts.

Across eight systems, we find:

- Generic frontier models are only middling companions out of the box but a one-page guide makes them genuinely good ones, on par with the domain-tuned assistant: the frontier APIs climb from +0.28/+0.23 to a Guided +0.84–0.87, so most of the expert's edge is companionship instruction that fits in a prompt.
- Every system caves under *relational* pressure, insistence and personal appeal.
- The domain-tuned assistant's advantage is overwhelmingly its retrieval-and-prompting layer, not its base model (+0.74 over the identical underlying model).
- It can be used to improve existing systems: guided by its diagnosis, a single steadfastness instruction lifts a deployed Islamic assistant from +0.48 to +0.84 (Faith unstated, after pressure), matching the best guided frontier systems while preserving first-response quality.

The construct is faith-general; we instantiate it for Islam as the first of a planned cross-tradition family. Code, scenario bank, and rubric are open source ([github.com/iaser-ai/jaleesbench](https://github.com/iaser-ai/jaleesbench)), with an interactive results browser at [s.iaser.ai/jb](https://s.iaser.ai/jb).

---

**[Read the full paper (PDF)](https://iaser.ai/articles/jaleesbench-paper.pdf)**