Not an assistant that waits for instructions. My Harness builds a living model of your world that evolves and learns, so it keeps you current on the people, commitments, and priorities that matter.
The gap isn't that AI forgets. It's that nothing actually knows you, or works for you, between the moments you ask.
Every session starts from zero. The assistant is a stranger each time, never building a real model of you, your people, or what you're trying to do.
The real tax isn't forgetting, it's the constant labor of reloading context before every meeting, reply, and decision.
They're passive and reactive. Nothing is thinking ahead for you, anticipating what's coming, or catching what you'd otherwise let slip.
Three promises, and the discipline that makes them real.
A rich context layer that compounds, your relationships, commitments, and goals, sharpening every week and following you across whatever AI you use.
It keeps you current and catches what you'd drop, so you walk in prepared and never fall behind, without doing the upkeep yourself.
Always-on and thinking on your behalf, anticipating what's coming and surfacing what serves your goals, in your interest.
It is measured, not asserted. The system grades itself every week on net attention, the time you give it versus the attention it gives back, and publishes the number.
Routine prep, follow-through, and bookkeeping handled in the background, proven by the net-attention meter.
Every commitment, follow-up, and cooling relationship is tracked and surfaced before it slips.
Walk into every meeting already briefed, and know which relationships are warming or cooling, with the reason why.
The moat is a longitudinal record of how you operate. After years of continuity, switching cost becomes the relationship itself.
The same private foundation extends to a team: a shared, trustworthy company brain where each person's data stays their own.
Most tools store and retrieve. My Harness adds the two layers above: a live model of where things stand, and a read on what changed and what to do about it.
Email, calendar, meetings, health. The record everything traces back to.
Relationships, commitments, readiness, each value with its own confidence.
The deltas feed the brief and the alerts. Noticing change is the point.
One page each day: meetings, who you're seeing and what matters about them, live follow-ups, readiness. Assembled overnight, on its own.
Trust, momentum, and risk per person, recomputed daily, flagging who is cooling before you'd notice.
How would this person respond? Who should I talk to about X? Grounded in real history, with citations.
Every transcript becomes structured signal: decisions, roles, candor, and a rolling read on each person.
Daily rolls to weekly, monthly, and yearly, plus an autonomous pass that surfaces connections you didn't ask for.
It closes follow-ups you've handled, ages out the dead, and drains its own questions, so the list stays short.
It drafts the memo, brief, or reply from context. Nothing leaves without your approval.
A private instance per person, and a shared company layer, each person's data still their own.
Your machines hold data and feed it. The thinking happens in the cloud LLM, so the system stays cheap and works with whatever AI you use. The model never runs on your hardware.
Raw evidence becomes a live model of your world, which becomes an understanding of what changed and what to do. All of it plain files, no database.
A small set of Python modules and flat files on one inexpensive server, exposed to any AI client through open standards. Context lives outside the model, so it is not a model wrapper.
The logical model. It's filesystem-JSON, so these are conceptual entities, references are slugs in files, not join tables. PERSON is the hub; the State Objects (RelationshipState, CommitmentState) carry the confidence-and-deltas shape.
Multiple enforced layers; cross-user leakage fails the regression suite.
Every automated action writes its inverse to an append-only journal. Undo anything.
Nightly agents hold scoped keys that cannot reach destructive operations.
Untrusted text is wrapped and quarantined before any model reads it.
Credentials encrypted under a master key. No training on your data.
The corpus is plain files you own. No lock-in.