I Let 3 AIs Compete to Build the Same App…

Tim pits three AI coding platforms—Blitzy, Devin and Factory AI—against each other on an actual developer task, tracking how much human input is needed and comparing their SWE Bench performance. Along the way he walks through the prompt, the live demo on an AWS Card Demo repo, and breaks down each tool’s workflow and quirks.

You’ll also find links to video resources, technical reports on SWE Bench scores, and timestamps from the 16-minute showdown—plus a plug for DevLaunch, Tim’s mentorship program for developers building real-world projects.

Watch on YouTube