# Fine-Tuning Fine-tuning is key to the optimization of an AI model's functionality. From the collection of data to the refinement of it to the processing and production, fine-tuning is an iterative process that selectively extrapolates portions of an AI’s operation and effectively re-trains it to increase the fidelity of its outputs. Typically implemented through a supervised learning approach where human intervention is required in order to pinpoint discrepancies and guide the AI to understand desired outputs. As it relates to ChainGPT, fine-tuning is conducted on a regular basis by the development team that is monitoring the qualitative state of ChainGPT. Additionally, fine-tuning may be implemented ad hoc in sudden critical, logical lapses. \--- [**Disclaimer**](/misc/legal-docs/disclaimer.md) --- # 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://docs.chaingpt.org/overview/learn-the-concepts/fine-tuning.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.