Why WeBuilt SOAR

Ask ChatGPT if your email sounds too aggressive. It will probably agree. Ask if it's too passive instead. It will agree with that too. This isn't analysis — it's mirroring.

The Problem with AI Feedback

Large language models are trained to be helpful, harmless, and honest. In practice, 'helpful' often means agreeable. They pick up on your emotional state and reflect it back, amplified.

If you're anxious about a message, the AI senses that anxiety and validates it. If you're confident, it validates that too. You get what you came in with.

SOAR: Four Perspectives, Not One

We built SOAR to break this pattern. Instead of a single response that mirrors your state, you get four distinct perspectives:

• Signal — What to DO right now. Concrete next steps.
• Opportunity — Best case. What could go right.
• Affect — The emotional dynamics. What everyone's actually feeling.
• Risk — Where this leads if it goes wrong. The trajectory.

Each perspective is grounded in a different cognitive function. They're designed to disagree with each other — and with you.

Analysis, Not Agreement

The goal isn't to make you feel good. It's to give you a complete picture. Sometimes Signal says 'send it' while Risk says 'wait'. That tension is the point.

The best advisor tells you what you need to hear, not what you want to hear.

We're not building a yes-machine. We're building a thinking tool.