I ve been exploring a rules + LLM approach where you write plain-text rules (any language) and the system makes approve/flag/reject decisions in under ~500ms, with priority to resolve conflicts.
What I d love feedback on:
Is priority the right way to resolve rule clashes (e.g., Personal Attack 0.9 > Verified 1.0 auto-approve)?
Most moderation APIs just detect bad words.
Moodiqo understands context — you can write rules like: “Reject if someone praises politician A but insults politician B.”
Define logic, any language, all under 500 ms. ⚡️
