# Memory Solution The majority of the weightings will be frozen after we have trained the model to fit into a "Domain specific" area (Specificity). Some of the weighting will remain free to change, around 15-20% estimated on average. This is represented in Yellow bellow:

This is where the personalization comes from - Your interactions will be stored as memories using the decoder model ([See Data Ownership](/skillful-ai-public-docs/memory-and-controlling-your-data/memory-solutions-and-user-data/data-ownership.md)) along with modifying specific traits (These "traits" are used to give context to answers, think tone of voice). A robust and accurate "memory" system is vital to allowing the level of personalization and specialty we will have in our models. The exact details and specifics for this will be released when we publish our developer documents. Early access developers will have more insight to allow them to fully test the system.\ \ See the whitepaper on our website for more information regarding this --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://skillful-ai.gitbook.io/skillful-ai-public-docs/memory-and-controlling-your-data/memory-solutions-and-user-data/memory-solution.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.