# AI system baking
<a name="raisp02"></a>


| RAISP02: How will you design the core AI system to meet the release criteria (baking)? | 
| --- | 
|   | 

 Baking implements features directly in the core AI system, for example through choices of component model types, objective functions, training datasets, and training strategies. 

**Topics**
+ [RAISP02-BP01 Design the core AI system to directly address your release criteria](raisp02-bp01.md)
+ [RAISP02-BP02 Privacy: Build privacy-preserving mechanisms into the core AI system](raisp02-bp02.md)
+ [RAISP02-BP03 Mitigate unwanted bias directly in the core AI system design](raisp02-bp03.md)
+ [RAISP02-BP04 Build security protections directly into the core AI system design](raisp02-bp04.md)
+ [RAISP02-BP05 Embed provenance indicators into core AI system outputs](raisp02-bp05.md)
+ [RAISP02-BP06 Enable users to customize core AI system behaviors](raisp02-bp06.md)
+ [RAISP02-BP07 Incorporate explainability mechanisms into the core AI system](raisp02-bp07.md)
+ [RAISP02-BP08 Consider core AI system designs that improve factual accuracy](raisp02-bp08.md)
+ [RAISP02-BP09 Design your core AI system to handle input variations](raisp02-bp09.md)
+ [RAISP02-BP10 Build safety protections into the core AI system](raisp02-bp10.md)