Request a Review

See where an asset follows your brand guidance and where it needs attention, with verdicts, explanations, and evidence pictures you can share.

This feature is in beta. During beta, endpoint schemas and behavior may change or be removed.

What the Review checks

Rainbrand checks one asset’s colors, typography, logo, and copy against your brand guidance. It looks for palette and font mismatches, incorrect or unreadable logos, and problems with spelling, grammar, expected text, brand facts, or voice. It does not judge your overall brand identity or personal taste. For example, a finding might say: “The headline uses a different font from the brand’s heading font,” with an evidence picture showing the mismatch. Each requested check returns pass, fail, uncertain, or not_applicable, a short reason, and evidence pictures where available. Unreadable text or insufficient brand evidence can produce uncertain. not_applicable means no relevant element exists; it is not a pass.

See a review example

This Adesso Bakeshop gift-box creative shows how a review identifies parts of an image and compares them with brand references.

Detected regions for copy, color, typography, and logo checks.

The evidence below shows the color, typography, and logo comparisons.

Color
Typography
Logo

Extracted colors compared with the brand palette.

Request and retrieve a Review

You’ll need a brand ready for Reviews and one image. Reviews accept PNG, JPEG, WebP, GIF, and SVG images, including any reference images you provide. Documents such as PDFs are not supported. For a local image, follow Upload local files first.

With your API key, submit the asset and checks:

curl -X POST https://www.rainbrand.com/api/v1/reviews \
  -H "x-api-key: $RAINBRAND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "brandSessionId": "<brand_session_id>",
    "assets": [{ "url": "https://assets.example.com/banner.png" }],
    "checks": ["color", "typography", "logo", "copy"]
  }'

Replace the Brand ID and image URL. You can also supply a temporary upload or an image ID, and add context such as expected text or comparison images. See Request a Review for those fields.The 202 response contains data.id and data.status. Set REVIEW_ID to that ID:

curl "https://www.rainbrand.com/api/v1/reviews/$REVIEW_ID?wait=true" \
  -H "x-api-key: $RAINBRAND_API_KEY"

Repeat this read while pending or processing. Completed checks appear under data.results. If the Review fails, read the error before retrying. See Get a Review for the result and error fields.

Connect your agent, then ask:

Review the Acme launch banner against its brand. Check colors, typography,
logo, and copy. The headline should read exactly “Meet your morning.”
Show me the findings and evidence pictures.

The agent requests the Review, waits for it to complete, and shows the findings and evidence pictures.

Use Reviews in an agent workflow

Use Review findings to guide revisions in your own image tool or a model that supports image references. Reviews never edit assets automatically. Limit the number of attempts to avoid unnecessary generation costs. Try this with your MCP-connected agent:

Generate an Acme coffee launch banner with the headline “Meet your morning.”
Wait for generation to complete, then review all four checks.

Fix only clear failures, with at most two editing rounds. After each completed
edit, review the revised image. Stop if an operation fails, the image stops
improving, or all applicable checks pass. Bring uncertain findings to me.
Do not add absent elements just to satisfy a check marked not_applicable.

Show the final image, remaining issues, and evidence.

Getting started

Guides

Use cases

MCP

What the Review checks

See a review example

Request and retrieve a Review

Use Reviews in an agent workflow

​What the Review checks

​See a review example

​Request and retrieve a Review

​Use Reviews in an agent workflow

What the Review checks

See a review example

Request and retrieve a Review

Use Reviews in an agent workflow