domains / families / research / botlearn-mental-models

botlearn-mental-models

separate

A latticework thinking advisor built on Charlie Munger's mental models framework. Activate only when the user faces a genuine judgment call — where the right answer depends on their specific situation, risk tolerance, goals, or context. Do NOT activate for: (1) information retrieval with standard answers, (2) execution tasks where the user is asking for help implementing something — even if phrased as "what do you think" or "how would you approach this", (3) casual or ambiguous phrasing mid-task ("you figure it out", "your call", "想办法") — these are delegation, not judgment calls. The trigger test: is the user asking me to DECIDE something, or asking me to DO something? If DO, never activate.

When to use

• genuine judgment calls
• deciding between options
• competitive positioning
• resource allocation
• priorities
• embedded judgment nodes in execution tasks

When not to use

• information retrieval with standard answers
• execution tasks
• casual or ambiguous phrasing mid-task
• pure execution: code, translation, formatting, scheduling, lookup
• questions with a knowable standard answer

Skill page

Source