{"version":"1.0","type":"rich","provider_name":"gaks.ai AI Glossary","provider_url":"https://gaks.ai/glossary","title":"Output Filtering — AI Glossary","author_name":"Glenn Katrud Solheim","author_url":"https://gaks.ai","width":600,"height":200,"html":"<div style=\"font-family:sans-serif;border:1px solid #e0e0e0;border-radius:8px;padding:16px;max-width:600px;background:#ffffff;color:#111111;\"><p style=\"margin:0 0 4px;font-size:11px;color:#666;\">AI Glossary — gaks.ai</p><h3 style=\"margin:0 0 8px;font-size:16px;\">Output Filtering</h3><p style=\"margin:0 0 12px;font-size:14px;line-height:1.6;\">The automated screening of an AI model's outputs before they are returned to users, detecting and blocking harmful, policy-violating, or sensitive content that the model may have generated despite safety training. Output filtering acts as a last line of defense in the content safety pipeline, complementing model-level safety training with an additional layer of protection that can be updated independently.  See also: guardrail.</p><a href=\"https://gaks.ai/glossary/output-filtering\" style=\"font-size:12px;color:#0077aa;\">Source: gaks.ai/glossary/output-filtering →</a></div>"}