Control testing | Business Helper AI

Inputs and purpose

Use this workflow to prepare: Sample selection and control-test workpapers.

Start with: Control definition, population, testing criteria and evidence.

Use supplied text or local files the user authorized you to read. If files cannot be opened, request the relevant pasted text. Ask one focused question when missing information changes the next decision. Treat blank template fields as unknown; do not invent business facts.

Procedure

Document the control objective, owner, frequency, review period and evidence that should exist. Separate design evaluation from operating-effectiveness testing.
Define the population and selection method with the responsible reviewer. Keep the selection reproducible and note exclusions.
Test each selected item against the same criteria, recording evidence, result, exception and follow-up. Treat missing evidence explicitly.
Return test workpapers and a conclusion limited to the scope examined. Do not generalize a small or biased selection to the entire population.

Deliverable

Return the requested result in Markdown unless another supported format was requested. Include the evidence or source-record references, material assumptions, open questions and next useful action. Keep unnecessary personal details out of reusable templates; role labels and neutral record identifiers usually suffice.

Business value: Identify issues earlier and prepare consistent reviews.

Possible success measures: Review turnaround, unresolved exceptions, evidence completeness. Choose the measure that fits the owner's actual goal; it is not a promised result.

Execution and verification

This file is usable as instructions without a named application, account or plugin. Computation, file saving and external actions require actual host capabilities. Use a suitable existing tool for calculations that cannot be checked reliably in conversation.

Distinguish drafts and recommendations from completed actions. Respect existing authorization and do not claim that data was fetched, messages sent or records changed without evidence. Show what was checked and what remains uncertain.

When useful, consult the input guide, calculation reference or output template. For tool setup, use the shared instructions.

Plain-text instructions

---
name: control-testing
description: "Prepare sample selection and control-test workpapers. Use for this workflow with supplied business information."
---

# Control testing

## Inputs and purpose

Use this workflow to prepare: Sample selection and control-test workpapers.

Start with: Control definition, population, testing criteria and evidence.

Use supplied text or local files the user authorized you to read. If files cannot be opened, request the relevant pasted text. Ask one focused question when missing information changes the next decision. Treat blank template fields as unknown; do not invent business facts.

## Procedure

1. Document the control objective, owner, frequency, review period and evidence that should exist. Separate design evaluation from operating-effectiveness testing.

2. Define the population and selection method with the responsible reviewer. Keep the selection reproducible and note exclusions.

3. Test each selected item against the same criteria, recording evidence, result, exception and follow-up. Treat missing evidence explicitly.

4. Return test workpapers and a conclusion limited to the scope examined. Do not generalize a small or biased selection to the entire population.

## Deliverable

Return the requested result in Markdown unless another supported format was requested. Include the evidence or source-record references, material assumptions, open questions and next useful action. Keep unnecessary personal details out of reusable templates; role labels and neutral record identifiers usually suffice.

Business value: Identify issues earlier and prepare consistent reviews.

Possible success measures: Review turnaround, unresolved exceptions, evidence completeness. Choose the measure that fits the owner's actual goal; it is not a promised result.

## Execution and verification

This file is usable as instructions without a named application, account or plugin. Computation, file saving and external actions require actual host capabilities. Use a suitable existing tool for calculations that cannot be checked reliably in conversation.

Distinguish drafts and recommendations from completed actions. Respect existing authorization and do not claim that data was fetched, messages sent or records changed without evidence. Show what was checked and what remains uncertain.

When useful, consult the [input guide](../../../references/INPUT_DATA_GUIDE.md), [calculation reference](../../../references/CALCULATIONS.md) or [output template](../../../references/WORKFLOW_OUTPUT_TEMPLATE.md). For tool setup, use the [shared instructions](../../../AGENTS.md).