Model

An agent-native document model built on explicit boundaries.

Nyxdoc is architected on a fundamental principle: reading, writing, and review must each expose a visible contract. This transforms agent collaboration from probabilistic guesswork into an auditable system of record.

Shared operating loop
Read

Structural discovery before context retrieval

The system should know what the document contains before it decides what to fetch in full.

Write

Commit bounded changes against explicit revision edges

Patch-first writing keeps responsibility, conflict detection, and rollback visible.

Review

Keep oversight native to the product, not lost in scattered process glue

Comments, diffs, and status need to stay attached to the document state they are about.

Each layer is narrow on purpose.

Our model thrives on restraint; every operation is scoped rather than rewritten. This precision is what makes automation more dependable, not less capable.

Read

Manifest-first structural discovery

Discover structure, section metadata, and addressable blocks first. Fetch only the blocks a task actually depends on.

Write

First-class patch and commit workflows

Changes should carry preconditions, revision boundaries, and a history that explains how the current state was produced.

Review

Comments as structured work units

Discussion is not side decoration. It becomes the bridge from human instruction to agent execution and back to review.

The point is not full automation. The point is bounded work.

01

A person leaves a scoped instruction

The task starts on a specific block, section, or document area instead of in a vague request disconnected from context.

02

An agent reads only what it needs

Context loading becomes intentional, cheaper, and easier to explain back to a reviewer.

03

The system records a verifiable patch

Every important change stays attributable, diffable, and tied to a known revision boundary.

04

Review and rollback remain calm

Oversight becomes a native product interface, replacing the manual reconstruction of past context.

The model’s utility depends on a restrained design philosophy.

Read the philosophy behind calm interfaces, visible change, and human judgment that remains explicit.