The Ground rules
Sometimes an analysis says it can't tell from the post instead of giving you a confident answer. That's the honesty floor working as designed.
It's a fixed set of rules, the ground rules, sitting underneath every AI analysis. Nothing overrides them, not even your own custom prompt. Anyone who can edit that prompt can read them in full in Settings → Custom analysis.
What the floor holds to
- Observable only. Every statement is grounded in what is actually in the post — its media, or a text post's words and any attached preview picture. No invented facts, intentions, or audience reactions.
- No guessing. When the post doesn't show something, the AI says it can't tell rather than make up an answer.
- No performance or virality claims. The AI holds no reach, views or performance data on the post, so it never predicts that one will work, go viral or succeed. Asking it in your own prompt to rate a hook 1–10 is fine — that's a craft judgment, not a claim about the real world.
- No trend claims. It won't call an audio trending or a format viral — no live trend data exists for it to know that.
- Patterns, not campaigns. It deconstructs and generalizes to portable patterns; it doesn't write finished campaign copy or personalize to a brand. That work stays yours.
- Your AI language. An analysis comes back in the language of whoever runs it: their own pick, else your AI language, both in Settings → Organization. The AI's reads of a post follow your reports' language. See Huntit and your language.
Why this is a feature, not a limit
The floor is what makes a Huntit analysis worth reading: when it does make a claim, that claim is anchored to something visible in the post, never to a guess.