Uploaded May 2026 | Updated September 2026, 1 hour ago
In this video, I walk through both ways to work with Devin: the cloud agent and Devin for Terminal. You'll see how each session runs in its own isolated environment with a dedicated VM, browser, IDE, and terminal.
What's covered:
- Kicking off sessions from the web app, Slack, Linear, Teams, the Devin MCP, or the Devin API
- Live work logs, diffs, and Slack session updates
- Devin Review automatically catching and fixing a bug in a pull request
- Using "Test the App" to have Devin boot, test, and record a screen capture of your application
- Jumping into the desktop and IDE to test the live or local version yourself
- Running multiple sessions in parallel, archiving, and scheduling (including a daily standup summary sent to Slack at 3 AM)
- Devin for Terminal: slash commands, model selection (including SWE 1.6 and SWE 1.6 Fast at 950 tokens/sec from Cognition)
- Using /handoff to send a long-running local session to the cloud while you keep working
- DeepWiki for deep codebase understanding, even on repos without a README
- Assigning Devin to tickets directly from Linear or Jira and watching session updates in real time
Whether you want a cloud agent handling PRs in the background or a CLI companion for local work, this should give you a solid overview of how Devin fits into a real engineering workflow.
🔗 Devin Docs
docs.devin.ai/get-started/devin-intro
🔗 Devin for Terminal
cli.devin.ai/docs
00:00 - Introduction
00:19 - Sending sessions to Slack
00:24 - Creating your first session
00:51 - Devin Review
01:20 - Computer Use testing
01:46 - Desktop and IDE in Devin
02:33 - Scheduled Devins
03:01 - Devin for Terminal
03:40 - Terminal to cloud handoff
04:09 - DeepWiki
04:21 - Assigning Devins from Linear
In this video, I walk through both ways to work with Devin: the cloud agent and Devin for Terminal. You'll see how each session runs in its own isolated environment with a dedicated VM, browser, IDE, and terminal.
What's covered:
- Kicking off sessions from the web app, Slack, Linear, Teams, the Devin MCP, or the Devin API
- Live work logs, diffs, and Slack session updates
- Devin Review automatically catching and fixing a bug in a pull request
- Using "Test the App" to have Devin boot, test, and record a screen capture of your application
- Jumping into the desktop and IDE to test the live or local version yourself
- Running multiple sessions in parallel, archiving, and scheduling (including a daily standup summary sent to Slack at 3 AM)
- Devin for Terminal: slash commands, model selection (including SWE 1.6 and SWE 1.6 Fast at 950 tokens/sec from Cognition)
- Using /handoff to send a long-running local session to the cloud while you keep working
- DeepWiki for deep codebase understanding, even on repos without a README
- Assigning Devin to tickets directly from Linear or Jira and watching session updates in real time
Whether you want a cloud agent handling PRs in the background or a CLI companion for local work, this should give you a solid overview of how Devin fits into a real engineering workflow.
🔗 Devin Docs
docs.devin.ai/get-started/devin-intro
🔗 Devin for Terminal
cli.devin.ai/docs
00:00 - Introduction
00:19 - Sending sessions to Slack
00:24 - Creating your first session
00:51 - Devin Review
01:20 - Computer Use testing
01:46 - Desktop and IDE in Devin
02:33 - Scheduled Devins
03:01 - Devin for Terminal
03:40 - Terminal to cloud handoff
04:09 - DeepWiki
04:21 - Assigning Devins from Linear
