flâneur

The pain points of building a copilot - Austin Z. Henley

austinhenley.com · 951 words · saved by 1 readers

This post is an informal summary of our paper, "Building Your Own Product Copilot: Challenges, Opportunities, and Needs". See the preprint for more details. Thanks to my collaborators at Microsoft: Chris Parnin, Gustavo Soares, Rahul Pandita, Jessica Rich, and Sumit Gulwani. Companies everywhere are launching copilots—AI assistants that leverage LLMs to assist with tasks. For example, Office Copilot helps you with Word and Excel, GitHub Copilot helps you write code, Intuit Assist helps with filing taxes in TurboTax, Adobe Firefly helps you generate and edit images, and Dropbox AI answers questions about your documents. Towards this, we conducted semi-structured interviews with 26 developers from a variety of companies that are working on copilots. We qualitatively analyzed their responses to identify themes. Then we conducted two focus group sessions with tool builders that involved reviewing our interview findings and brainstorming possible solutions. Given the nondeterministic nature

The pain points of building a copilot - Austin Z. Henley Austin Z. Henley I build tools for people austin.henley@microsoft.com @austinzhenley github/AZHenley Home | Publications | Teaching | Blog The pain points of building a copilot 2/4/2024 See the discussion of this post on Hacker News . This post is a summary of our SANER'25 paper, "Building Your Own Product Copilot: Challenges, Opportunities, and Needs". See the paper for more details. Thanks to my collaborators at Microsoft: Chris Parnin, Gustavo Soares, Rahul Pandita, Jessica Rich, and Sumit Gulwani. Companies everywhere are launching c

related reading