AI Brand Voice Check tool
The AI Brand Voice Check tool evaluates each block's source text against a brand voice profile using a configured LLM provider. The model returns findings across voice dimensions — tone, style, clarity, and brand compliance — each with a severity, message, and suggestion. The tool computes an overall brand-compliance score, records the score and any findings on the block's properties, and attaches a brand-voice annotation to the block. Blocks with empty source text are skipped.
Provider credentials are required, since the tool makes an external API call per block. The voice profile that defines the brand's guidelines is supplied by a profile identifier resolved from the store, or programmatically by the host (for example the brand command or a project's brand binding). This is the LLM-based companion to the rule-based brand vocabulary check.
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
apiKey | string | API key for the AI provider | |
model | string | AI model name | |
profileId | string | Brand voice profile to resolve from the store | |
provider | string | anthropic | AI provider |
Configure these parameters interactively and copy the flow-step YAML on the Tool Reference.
Examples
Check against a stored profile
Resolve a named brand voice profile and evaluate text against it.
provider: anthropic profileId: acme-marketing
Processing notes
Operates on blocks; blocks with empty source text are skipped.
Blocks are processed in parallel by default for throughput.
A brand-voice score and findings are stored on the block, and a brand-voice annotation is attached.
Limitations
Requires AI provider credentials; makes an external API call per block.
Without a resolved voice profile, the prompt has no brand guidelines to check against.
Evaluates source text; findings are model output and reflect the chosen model's judgement.
← Back to the Tool Reference