Abstract
Keeping product documentation in synchronization with a product as the product is updated requires significant manual effort and can be prone to human error. This disclosure describes techniques to automatically update documentation when changes are made to a product or system covered by the documentation. Per the techniques, embeddings are generated for individual documents (or sections thereof) in the documentation corpus. As the product or system is updated, the corresponding changes are recorded, e.g., in an updated codebase for a software product, design and/or hardware specifications for a hardware product, etc. New embeddings are generated for the updated information based on these recorded changes. The new embeddings are compared with pre-computed stored embeddings of the documentation to determine documents (or sections thereof) that are impacted by the change to the product. A text generation model is then used to update the documentation with the new information in the recorded changes. The text generation model can be provided with a prompt instructing the model to fix discrepancies between the documentation and the new information.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Basques, Kayce and Kearney, Meggin, "Product Documentation Updates Using Artificial Intelligence", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/8057