Privacy & classroom rules

Useful learning.
Visible control.

Teaching an agent should create inspectable state, not invisible memory or authority nobody can review.

NON-NEGOTIABLEPrivate files never become public by accident.ONE AGENT · APPROVED FILES · HUMAN ACTIONS
01

One agent is enough.

The first product avoids company administration and agent fleets. Each private classroom owns one clear agent and one history.

02

Files are cognitive memory.

AGENTS.md, knowledge, teacher explanations, procedures, corrections and YAML rules remain visible—not hidden conversational state.

03

Approval changes state.

A proposed training file is not active. A draft is not published. The interface always shows the real status.

04

Uncertainty becomes a question.

After you press Process, the agent asks about authority, scope and exceptions instead of inventing certainty. Binary questions get quick replies.

05

Public means fabricated or reviewed.

Current public demonstrations are entirely fictional. Private uploads, emails and output files do not appear there.

06

Real actions remain human.

Publishing, sending, buying and changing external systems require a separate human-controlled execution step.

Technical truth

“Teaching” does not secretly mean changing model weights.

The framework creates durable agent files, source-grounded context, revisions and approval history. A self-hosted installation may connect a model, but the files remain the authoritative training record.