This blog covers the Sofer Mahir project. This project funded by a private foundation for the period from September 2018 until August 2021 deals with the application of cutting edge document analysis, handwritten text recognition and other machine learning on manuscript images of several European and American libraries and the National Library of Israel for the creation of an open source repository for precise transcriptions of tannaitic rabbinic literature. Expected readers include scholars in Jewish studies and manuscript studies as well as digital and computational humanities. This project is in close interaction but distinct from the Tikkoun Sofrim blog. The Hebrew expression Sofer Mahir means “tachygraph” while Tikkoun Sofrim means “scribal correction”. The first deals mainly with automatic layout analysis and automatic transcription while the second deals mainly with the application of gamification, machine learning and crowdsourcing to correct these automatic transcriptions. They run over different periods.