> ## Documentation Index
> Fetch the complete documentation index at: https://www.docs.forgeshipyard.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Where Humans Stay in Control

> The decisions that always belong to a person, by design.

export const Abstention = () => <Tooltip tip="When the AI declines to answer because it is not confident enough. In Forge this is treated as a good behavior, not a failure.">abstention</Tooltip>;

export const Capability = () => <Tooltip tip="A named, versioned, rule-bound move the AI is allowed to make. The AI cannot invent new moves on the fly.">capability</Tooltip>;

<Note>
  **In plain terms:** Forge's AI can do a lot of the legwork, but certain decisions
  always belong to a human. This is built into the structure of the system, not left
  as a setting someone could turn off.
</Note>

## The three operating principles

Every design choice in Forge maps back to one of three principles:

<Steps>
  <Step title="Sources have authority. Every claim cites.">
    Every document that enters Forge is graded by trust level before it is used. A
    claim that a rule applies must cite that rule and its version. Nothing the
    system says is ungrounded.
  </Step>

  <Step title="Decisions are first-class objects, not log lines.">
    Every engineering decision is recorded with the inputs it was made from, the
    rule version it was made under, the evidence it cited, who made it, and a
    signature that makes it tamper-evident. When a rule later changes, the system
    can find every decision that needs re-checking.
  </Step>

  <Step title="AI proposes; humans decide; the gate is structural.">
    The AI can retrieve, compare, draft, flag, and propose. It cannot be the design
    authority. Decisions touching class, USCG, or safety always pass through a
    human approval gate. This is not a setting that can be disabled.
  </Step>
</Steps>

## What humans always own

The system is intentionally designed so that humans remain authoritative on:

<CardGroup cols={2}>
  <Card title="Class and USCG decisions" icon="scale-balanced">
    Every class-touching or USCG-touching decision requires human approval at the
    final gate, by structure.
  </Card>

  <Card title="The shape of what's known" icon="sitemap">
    Every change to the underlying model of what kinds of things exist is governed
    by humans, never by the AI.
  </Card>

  <Card title="What the AI may do" icon="list-check">
    Every change to the catalog of allowed AI moves goes through a review checklist
    before it ships.
  </Card>

  <Card title="Unsure outputs" icon="circle-question">
    Whenever the AI is low-confidence or abstains, the system surfaces the question
    and a human answers it.
  </Card>

  <Card title="Production readiness" icon="circle-check">
    Every sign-off that a build is ready for production is a human decision.
  </Card>
</CardGroup>

## Abstention is a feature, not a bug

A key part of keeping humans in control is that the AI is built to **stop when it
is unsure.** <Abstention /> is treated as a quality behavior. If the AI cannot find
the evidence it needs, it asks for more rather than guessing. The system is held to
a high bar for doing this well (a target of better than 98%).

The result is an AI that is **boxable, auditable, and reversible.** If a behavior
turns out to be wrong, it gets rolled back like any other versioned software
change, never patched on the fly. For the full list of limits, see
[What Forge Will Not Do](/start-here/what-forge-wont-do).