Back to work archive

CASE / AURA

AURA

A controllable and transparent AI companion designed to avoid dependency-inducing patterns.

Role
Product, safety, and conversation experience
Category
ai

Problem

AI companionship needs transparent privacy and safety boundaries alongside continuity, memory, and persona.

Decisions

Validate stable conversation, persona policy, a user-controlled memory bank, and safety gates before avatars or monetization mechanics.

Outcome

The project record identifies the product as an Internal Alpha and documents its service baseline and release gates.

Reflection

Companion quality is not only about feeling human; users also need to understand what the system is doing.

Public evidence

  • Internal Alpha briefAURA project README, reviewed 2026-07-17