{"id":663303,"date":"2020-05-29T14:19:34","date_gmt":"2020-05-29T21:19:34","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-group&p=663303"},"modified":"2024-09-16T11:25:55","modified_gmt":"2024-09-16T18:25:55","slug":"prose","status":"publish","type":"msr-group","link":"https:\/\/www.microsoft.com\/en-us\/research\/group\/prose\/","title":{"rendered":"PROSE"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"PROSE\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

PROSE<\/h1>\n\n\n\n

AI-Assisted Programming<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n

<\/p>\n\n\n\n\n\n\n\n

The PROSE research and engineering team, led by Sumit Gulwani<\/a>, develops program synthesis APIs over a wide variety of modalities \u2014 programming by examples (PBE), natural language, temporal context \u2014 with applications in diverse areas such as assisting sloppy programmers through automatic program repair and conversational AI.<\/p>\n\n\n\n

Programming by examples (PBE) is a new frontier in AI that enables users to create scripts from input-output examples. PBE can provide a 10-100x productivity increase for developers in some task domains. About 99% of computer users are non-programmers and PBE can enable them to create small scripts to automate repetitive tasks. Moreover, PBE is revolutionizing data wrangling as well, as data scientists spend up to 80% time transforming data into a form suitable for machine learning (ML). We own part of the AI surface for mass-market products over four customer segments: developers (Visual Studio (opens in new tab)<\/span><\/a>, VS Code (opens in new tab)<\/span><\/a>), data scientists (Notebooks (opens in new tab)<\/span><\/a>), low-code\/no-code users (Excel (opens in new tab)<\/span><\/a>, Power Apps (opens in new tab)<\/span><\/a>, Power Automate (opens in new tab)<\/span><\/a>, Power Query (opens in new tab)<\/span><\/a>), and students (Github Education (opens in new tab)<\/span><\/a>).<\/p>\n\n\n\n

We advance the state of the art in program synthesis through innovations and deliver these innovations in mass-market products, as indicated by active customer usage and testimonials. We also heavily publish in top-tier conferences, which gained significant recognition and delivered impact over the broader research community. We empower our team members through the culture of strong collaboration within impactful projects, trusted relationships with product partners, and accelerate impact by giving back through mentorship to long-term interns and research fellows<\/a> (learn more about our research fellowship program<\/strong><\/a>). Our research culture<\/a> is based on: customer connection that enables us to pick the relevant problems, synergy between research and engineering<\/a>, an approach towards building foundational frameworks, and cross-disciplinary work.<\/p>\n\n\n\n

\n
Read about Flash Fill in Excel<\/a><\/div>\n<\/div>\n\n\n\n
\n