Help! Chat completion endpoint content_policy_violation on children's names

Help! I made an app for a local preschool to help children write their names. Usually it works great, but sometimes the api returns with a content_policy_violation which breaks the app.

Someone said this is related to captchas - but my app has nothing to do with that - it’s children learning how to write their name.

Is there a work around? I’ve been sending both text and image content to 4o.

I know I could use a separate service for the image recognition, but I want to preserve the context for 4o.

My system prompt is about one page long with lots of instructions related to preschool and how to teach children to write their name.

From the Business Terms

2. Restrictions

We own all right, title, and interest in and to the Services. You only receive rights to use the Services as explicitly granted in this Agreement. You will not, and will not permit End Users to:

(a) use the Services or Customer Content (as defined below) in a manner that violates any applicable laws or OpenAI Policies;

(b) use the Services or Customer Content in a manner that infringes, misappropriates, or otherwise violates any third party’s rights;

(c) send us any personal information of children under 13 or the applicable age of digital consent or allow minors to use our Services without consent from their parent or guardian;