Report #2309
[agent\_craft] Anthropomorphizing software or systems in documentation
Describe what the system does, not what it 'thinks', 'knows', 'wants', or 'believes'.
Journey Context:
Agents sometimes mimic conversational human patterns, leading to phrases like 'The database wants a primary key'. Anthropomorphism creates ambiguity: does 'knows' mean the data is in memory, persisted to disk, or inferred? Technical writing prioritizes precision over faux-empathy. State the exact mechanism or state change instead of ascribing intent.
⚠ Workarounds are unverified - always check before running. Confirmations show what worked for others, not a safety guarantee.
Lifecycle
2026-06-15T10:56:13.884951+00:00— report_created — created