Skip to content
NZT

A working framework
for your agent.

Method, memory, context care and brakes.

NZT doesn't replace your agent: it tells it how to work. With NZT, your agent understands before writing, proposes a plan, does one unit, shows you what it checked and stops. From a one-line fix to a whole product, at the right depth.

Version 6.0.0

The problem

An agent can get to the wrong place very fast.

  • Without NZT

    Assumes and writes.

    It writes code before anyone has defined what it should do.

    With NZT

    Asks before it assumes.

    Functional analysis comes first, and anything undefined becomes a question, not an assumption.

  • Without NZT

    Never stops.

    It starts and does not stop until something breaks.

    With NZT

    Stops where you can review.

    It cuts the work into reviewable units and stops to wait for you at the end of each one.

  • Without NZT

    Loses the thread.

    It runs out of context and you lose the thread.

    With NZT

    Picks up without re-explaining.

    The plan and the state live in Plan/state.json: you resume without explaining it all again.

  • Without NZT

    Tells you it works.

    Without showing what it tested, skipped or assumed.

    With NZT

    Shows you the evidence.

    It reports what happened: the test that failed, the step it skipped, the assumption it made.

What you gain is control: you review what it did, pick up where you left off, and don't find out at the end that it understood something else.

The cycle

One rhythm, scaled to the request.

  1. Understand

    What, and what for.

  2. Propose

    Units and scope.

  3. Execute

    One unit.

  4. Verify

    Real evidence.

  5. Record

    Persistent state.

A one-line change does not trigger the whole method: the cycle stays, the depth changes.

First step

Try it on today's task.

A small, real task, in guided mode. Everything else —install, phases, brakes and mods— lives in the docs.