Steve

The problem

Career plans unfold over months, while most AI conversations start without the decisions and context that came before. I wanted an adviser that could keep the whole picture in view without giving me generic career advice.

The approach

I built Steve around a long-term career direction, a live plan, a record of recent decisions, and clear rules for how he should challenge me. His job is to remember the context, make trade-offs clear, and test my thinking while leaving the final decision with me.

How it works

Steve reads a small set of files covering my long-term direction, current plan, and latest developments. He helps with weekly reviews, tracks dated commitments, challenges important decisions, and helps with drafts when I ask. He cannot contact anyone or take action outside the system.

Key decisions

• Base the character on the more measured, later-career Steve Jobs rather than the volatile caricature.
• Separate durable context, the live plan, and the recent log so old assumptions do not override new facts.
• Do not allow Steve to contact anyone or take external action. The final decision remains mine.

Current use

Steve remains in active use as a private career adviser. He gives longer-running career questions continuity and keeps a written record of what changed, what I decided, and what still needs attention.

What I’ve learned

Steve is useful because he remembers what I am trying to achieve, what changed, and why I made earlier decisions. The Steve Jobs character affects how he speaks, but the important work was deciding what he should remember, when he should challenge me, and when he should stop.