What problem does it solve? AI agents often ask users "who is X?" when the answer already exists in their knowledge base, wasting user attention on questions the system can answer itself. This Skill gates every identity, role, or relationship question behind an exhaustive lookup chain so the user is only bothered as a last resort. ## Core Features & Use Cases - Ordered Lookup Chain: Runs think/synthesis, search plus full page reads, mounted source queries (email, calendar, chat), timeline and graph traversal, then web search before any escalation. - Hypothesis-Led Escalation: When asking is justified, the question leads with a best-guess hypothesis, states what was searched and found, and uses a 2-4 option choice gate. - No-Placeholders-at-Ingest Rule: Post-ingestion passes resolve relationship and role fields on newly created people/company pages, eliminating placeholder text like "[To be filled by content analysis]". - Use Case: During a bulk email import that creates 100+ contact pages, run this Skill to fill each person's relationship and role from the imported signals, so briefings never show "unknown relationship" entries. ## Quick Start Before asking me who a contact is, run the full brain lookup chain and only escalate with a hypothesis if nothing resolves them.
