TESS has enabled the identification of thousands of planet candidates and hundreds of confirmed planets, opening up the possibility of demographic studies. However, the process of transit vetting and further confirmation of planet candidates is subject to time-consuming and biased manual inspection, highlighting the need for automatic pipelines. In this work, we perform statistical validation of planet candidates around main sequence stars with the new pipeline RAVEN, which allows for an entirely automated process from discovery to validation. We target all main sequence stars present in the TESS FFI SPOC ligthcurves characterised by Gaia (with Gaia magnitude brighter than 14, over 2.3 million targets). We conduct a BLS search on all SPOC FFI lightcurves and use RAVEN to vet and validate planet candidates. RAVEN probabilistically classifies transit candidates into planet candidates and false positives using machine learning algorithms trained with realistic synthetic lightcurves. We expect to be able to statistically validate multiple new planet candidates, enabling demographic studies in a uniform and well-defined sample.