{"id":"expert-prompt-paradox","text":"Telling an agent it is an expert reduces belief utilization. The humble generic prompt produces better results because the agent consults the knowledge base instead of trusting its 'expertise'","truth_value":"IN","source":"repo:beliefs-pi/entries/2026/03/15/beliefs-ablation-results-structured-knowledge-beats-prompt-engineering-expert-prompts-may-hurt.md","source_url":"","source_hash":"","justifications":[{"type":"SL","antecedents":["evidence-beliefs-ablation"],"outlist":[],"label":""}],"dependents":["how-agents-use-eem"],"metadata":{},"explanation":{"steps":[{"node":"expert-prompt-paradox","truth_value":"IN","reason":"SL justification valid","antecedents":["evidence-beliefs-ablation"],"label":""},{"node":"evidence-beliefs-ablation","truth_value":"IN","reason":"premise"}]}}