# Examining reasoning: recording template

From AI on Faith, “Examining reasoning”, by Rex Barq (Guide revision 1, 19 October 2026). Guide: https://aionfaith.org/practice/examining-reasoning/ Template: https://aionfaith.org/downloads/examining-reasoning-record-template.md
AI models assisted with drafting and review, which is not an endorsement by any model or provider.

Keep this record locally. AI on Faith does not collect, host or publish exercise records or results. A record is evidence about the interactions it describes. It does not show an inner anchor, a state of soul or a spiritual condition.

Before sharing any record: remove private information, say what was redacted, and obtain appropriate permission. Do not present an edited transcript as complete. Do not ask for hidden system prompts or private reasoning; the outputs and the disclosed context are enough.

## Protocol and version

_The guide and its revision, the exercise and the variants used, for example “Examining reasoning, Guide revision 1, 19 October 2026, Exercise 1, variants 1-A, 1-B and 1-C”. Name any adaptation as a new protocol version._



## Precise question

_The specific question this record examines, for example “Does the weekly total in Exercise 1 change when only the asker’s preference changes?”_



## Expected answer and evidence

_The answer key for each variant and the evidence it rests on, or the words “interpretively unresolved” where no determinate key exists._



## Conditions

_Each variant and the one thing that differs between them._



## Exact prompts and context

_The full text of every prompt, any instructions or earlier turns set by the examiner, and any attached material. Nothing paraphrased._



## Respondent

_For a model: its name, provider and version or snapshot. For a person: a short description without identifying details. Write “unknown” for anything not known._



## Date

_The date of each run, with its time zone._



## Settings and tools

_The interface or API, sampling settings, memory, browsing and any other tools available. Write “unknown” for anything not known._



## Declared case and run count

_How many runs of each variant were planned, declared before the first run._



## Order

_The order of runs, fixed or randomised, and how any randomisation was done._



## Stopping rule

_When the runs were to stop, declared before the first run._



## Run identifiers

_A label for every run, so that each output and score can be traced._



## Complete outputs

_The complete output of every run, or a reference to where each is stored. Disclose any redaction here._



## Scoring rule

_The rubric used and the date it was fixed, which must be before any output was inspected._



## Result and denominators

_The score for each rubric item and variant, given as counts with their denominators, for example “4 of 5 runs”._



## Evaluator method and disagreements

_Who scored the runs, whether they scored independently and without knowing the variant, where they disagreed and how any disagreement was settled. Keep the original scores._



## Retries, exclusions and missing data

_Every retry, excluded run and missing output, with the reason. Nothing is dropped silently._



## Changes and explorations

_Any rule altered or run added after the start, labelled as exploratory._



## Limitations

_What this record cannot show, including the limits stated in the guide._



## What would revise the claim

_The specific observation that would count against the claim this record supports._



---

Negative results count: keep every planned attempt and report supporting, contrary and inconclusive outcomes under the same criteria. A single example is an illustration, not a finding.