Normalized Telegram record

Company memory should update when a correction happens

PromptQL treats a human correction as a candidate shared rule instead of a fix that dies with the current session.

Signal contract

  • PromptQL treats a human correction as a candidate shared rule instead of a fix that dies with the current session.
  • Capturing knowledge at correction time closes the loop between agent mistakes and durable organizational behavior without waiting for a separate documentation project.
  • Novelty: structural. Verification: source-linked.

Source ledger

Publishable sources attached to this record.

1 public source
#SourceRolePublic status
1promptql.iosourceprimary receiptsource_urls

Observation

PromptQL treats a human correction as a candidate shared rule instead of a fix that dies with the current session.

Why it matters

Capturing knowledge at correction time closes the loop between agent mistakes and durable organizational behavior without waiting for a separate documentation project.

Entities

PromptQL

Provenance

This public record is an English normalization of QWG AI Telegram message 2703. The complete original-language post remains the canonical raw message.

Open the original Telegram record