We actually didn't want to build a 'plan mode' in Cline. It went against our core principle of simplicity. But then we saw how our power users were using Cline, and it became clear we had to.
Some behind-the-scenes on Plan mode & why it's a critical paradigm in AI coding 🧵
Some behind-the-scenes on Plan mode & why it's a critical paradigm in AI coding 🧵
Internally, and with our earliest users, we noticed a pattern. As the AI got more capable, people would instinctively say "wait, don't code yet" or "let me see a plan first." They needed a brake pedal for an AI that was too eager to help.
We were hesitant. Adding modes adds complexity, and we want Cline to feel intuitive. We debated it back in January, worried about forcing a specific workflow. The goal is to keep Cline feeling light and unopinionated.
But we realized this wasn't about forcing a workflow. It was about creating space for the most critical part of development: human intent. The AI can write the code, but only the human knows the WHY. Plan Mode became a necessary space for that dialogue.
So we stopped thinking of it as a "mode" and started seeing it as a paradigm. A deliberate separation between gathering intent (Plan) and executing on it (Act). It’s the same powerful AI throughout, just a different phase of collaboration.
(early concept)
(early concept)
What started as a reluctant feature has become a cornerstone of the Cline experience. It turns out that giving users a dedicated space to align with the AI before it acts leads to dramatically better outcomes.
It's been validating to see the broader AI coding community adopt similar planning phases recently. It confirms what we learned months ago: as AI gets more powerful, the space we create for human intent matters more than ever.
How do you see planning evolving?
How do you see planning evolving?
• • •
Missing some Tweet in this thread? You can try to
force a refresh
