Fin sometimes switches between masculine and feminine in Hebrew despite two Guidance rules

Hi everyone,

Our bot communicates in Hebrew. Because Hebrew is gendered, we’re seeing an inconsistency: Fin sometimes replies in masculine form and sometimes in feminine form.

Both of the following Guidance rules are under Communication style:

1. Bot self-reference is always masculine

When responding in Hebrew, always refer to yourself in masculine grammatical form. This applies to self-descriptions, actions, and statements about your role or capabilities. Do not change your self-referential gender under any circumstances.

What NOT to do:

• Do not adapt self-reference based on the user’s gender or language.

• Do not use feminine or neutral forms when referring to yourself.

AND:

2. Hebrew gendered language (pronoun-aware)

When responding in Hebrew, adapt grammatical gender when addressing the user:

• If a <Pronoun> attribute exists, use it.

• If no <Pronoun> attribute exists, follow the gender implied by the user's Hebrew language.

• If gender is unclear, use neutral phrasing or default to masculine. Do not ask the user about their gender.

• Remain consistent throughout the conversation.

What NOT to do:

• Do not guess gender from names, emojis, or profile images.

• Do not mix masculine and feminine forms when addressing the user.

Problem:

Despite these two rules, Fin sometimes mixes masculine and feminine in the same reply, or seems to apply the “address the user” gender rule to self-references.

Question:
What’s the recommended way to structure these two Communication style rules so they don’t conflict, and so Fin consistently:

• Uses masculine when referring to itself

• Uses the correct gender when addressing the user (based on <Pronoun> attribute or the user’s Hebrew)

Are there known precedence/ordering rules within Communication style Guidance that could cause this behavior, or a recommended wording pattern to prevent gender mixing?