---
title: Checking how a brand is described
description: Read sentiment and answer text to identify pricing or feature
  claims that need verification.
canonical_url: https://orchestor.io/docs/en/cli/workflows/brand-claims
markdown_url: https://orchestor.io/docs/en/cli/workflows/brand-claims.md
contentType: how-to
---

# Checking how a brand is described

Read sentiment and answer text to identify pricing or feature claims that need verification.

## When to use this workflow

> “Check whether AI describes our pricing and features accurately.”

## Before fetching

Establish the product, answer sample, authoritative pricing or specifications, and applicable dates. Verify concrete claims against facts for that product rather than inferring accuracy from sentiment.

## Quick reference

Use this sequence once you know the task. Read the numbered steps below for the reasoning and checks.

```bash
orc reports sentiment get --json
orc answers list --brand-id YOUR_BRAND_ID --json
orc answers get YOUR_ANSWER_ID --json
```

## Prerequisites

Complete the [CLI quickstart](https://orchestor.io/docs/en/cli/quickstart.md). These commands use CLI 0.5.0. Select the target workspace and use IDs returned by list commands.

Answers about the target brand and first-party information for checking claims.

Use sentiment to choose where to investigate, then check specific claims in the answer text.

## 1. Use sentiment to narrow the investigation

Use changes to select answers for inspection. A score alone does not determine whether a claim is wrong.

```bash
orc reports sentiment get --json
```

## 2. Find relevant answers

Filter by the target brand or prompt and check answer timestamps. Choose an answer ID returned by this list.

```bash
orc answers list --brand-id YOUR_BRAND_ID --json
```

## 3. Read the answer

Replace YOUR_ANSWER_ID with an ID from the list. Keep the actual answer wording and citation URLs.

```bash
orc answers get YOUR_ANSWER_ID --json
```

## 4. Verify and save the result

Record claims about prices, features, or comparisons with their answer IDs. Keep citation URLs when present and check claims against accurate first-party information. Sentiment alone does not identify misinformation or establish that a cited source caused a score change.

## When data is missing

If data is missing, check the workspace, collection period, filters, and pagination. Keep a failed request separate from an empty result. Use `--help` to inspect supported options.

## Related

[All workflows](https://orchestor.io/docs/en/cli/workflows.md) · [Global options](https://orchestor.io/docs/en/cli/global-flags.md)

If a failure remains, [report it and verify the fix](https://orchestor.io/docs/cli/workflows/workflow-feedback.md), including this workflow and the failed step.

---

[Documentation index](https://orchestor.io/docs/llms.txt)