Frank Lesniak<p>This week, while at <a href="https://infosec.exchange/tags/PSHSummit25" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PSHSummit25</span></a>, I worked on AutoCategorizerPS. This <a href="https://infosec.exchange/tags/PowerShell" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PowerShell</span></a> <a href="https://infosec.exchange/tags/datascience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>datascience</span></a> tool automatically categorizes text data when you do not know the categories/labels that best characterize the data. Link: <a href="https://github.com/franklesniak/AutoCategorizerPS" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/franklesniak/AutoCa</span><span class="invisible">tegorizerPS</span></a> <a href="https://infosec.exchange/tags/PSHSummit" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PSHSummit</span></a></p><p>Use cases: survey analysis, service desk ticket analysis, product review analysis, etc. If this sounds useful to you, check out the talk I gave with Danny Stutz from last year: <a href="https://youtu.be/Z08QCs_y1BU?si=6HRnOYv_RjU2M6yq" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/Z08QCs_y1BU?si=6HRnOY</span><span class="invisible">v_RjU2M6yq</span></a></p><p>(If you're wondering, I improved <a href="https://infosec.exchange/tags/AzureOpenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AzureOpenAI</span></a> support (now "production ready") and enhanced one of the scripts to support the latest <a href="https://infosec.exchange/tags/OpenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenAI</span></a> models.)</p>