Skip to content
Trending storyDeveloping

Stanford's CS146S course teaches AI-native engineering, with Monaco AI's Devin workflow as a case study

2 reports1 sourceupdated 16 hours ago

What happened

AI digest

On November 9, Latent Space reported that Stanford's CS146S course brought in open-source maintainers for its second run. Students had to get familiar with unfamiliar repositories, propose changes, and explain their patches to the people who might merge them. Instructor Mihail Eric, who also leads AI at Monaco, walked through the ten-week syllabus in an interview, covering coding agents, context engineering, and the skills needed to understand code diffs. A follow-up report the same day said the course covers agent internals, skills, code review and security, and includes a project contribution assignment where open-source maintainers review student patches. Eric also described Monaco's engineering practice: the team evaluated code review products, adopted Devin, and built its own agent workspace on its cloud environment so background agents can run the product, reproduce failures and test patches.

Written by AI from the coverage · updated 15 hours ago

Coverage

Follow the reports to see the story from different sides.

Nov 9
  1. Latent SpacePick
    Stanford's AI-native engineering course: Mihail Eric on CS146S and Monaco's agent setup

    Mihail Eric explains how Stanford's CS146S trains AI-native software engineers and how the course was designed alongside Monaco's team practice. The 10-week course covers coding agent internals, context engineering, skills, code review and security, and adds an open-source contribution assignment where maintainers review student patches. Monaco picked Devin after evaluating code review products, and built its own agent workspace on its cloud so background agents run the product, reproduce bugs and test patches.

  2. Latent Space
    [One Million AI Engineer Special] How Stanford Teaches AI-Native Engineering — Mihail Eric, Monaco

    斯坦福 CS146S 在第二轮开课时引入开源维护者,要求学生熟悉陌生仓库、提出修改,并向可能合并代码的人解释补丁。任课教师兼 Monaco AI 负责人 Mihail Eric 在访谈中展示了十周课程大纲,讨论编码智能体、上下文工程与理解代码差异所需的技能。

Heat over time

Heat now 6·Comparable peak 10(Nov 9 07:00)·Comparable change over 24 hours –

02.557.510Nov 907:00Nov 912:00Nov 916:00Nov 921:00

The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.