Cline

We're watching the beginning of the end for complex UIs. Those Blender AI demos going viral aren't just neat tricks -- they're early signals of a massive shift. We've all paid the "UI tax" for decades: spending weeks learning software instead of creating with it. MCP servers are just bridges right now -- translating what you want into the actions software needs to take. But they're proving something crucial: powerful tools don't require complicated interfaces. The greatest irony? Even "no-code" platforms ended up creating their own learning curves. At Cline, we're building for a world where you focus on what you want to accomplish, not how to navigate the tool. Your skills become transferable because you're communicating in plain language, not specialized interfaces. We don't need better UIs. Maybe we don't need UIs at all.

Selectable options transform how you work with Cline -- let us explain: Instead of typing open-ended responses, you can now choose from curated paths that Cline presents. This shifts Cline from just a tool to a true collaborative partner -- offering guidance while keeping you in control of the direction. Small UI change, profound workflow difference.

New in Cline 3.7.0: The .clinerules folder -- a better way to organize your project rules. Here's how you can implement a modular rules system that transforms how Cline understands your projects: ?? 1/ How it works: Any markdown files placed in the .clinerules/ folder are automatically aggregated and appended to your system prompt - exactly like the single .clinerules file, but with the flexibility of multiple files. 2/ This opens up a powerful organizational pattern you can implement: 1. Create a .clinerules/ folder for active rules 2. Create a .clinerules-bank/ folder for inactive rules you might need later Then simply move files between them as your context changes. 3/ This organization pattern isn't built-in, but it's how we recommend structuring your rules for maximum flexibility. Move files between folders to precisely control what context is loaded. Remember: Only files in .clinerules/ are active and added to your prompt. 4/ Recommended implementation for teams working with complex repos: 5/ When switching contexts, you could use file operations or simply drag files between folders to update your active rules: # Moving to a new client project mv .clinerules/current-client.md .clinerules-bank/clients/ cp .clinerules-bank/clients/client-b.md .clinerules/current-client.md 6/ For even more organization, we recommend structuring your rules bank hierarchically: - Global standards always stay active - Technology-specific rules rotate based on current stack - Client requirements change per project - Sprint priorities update regularly 7/ It's important to understand that all markdown files in the .clinerules/ folder are combined in alphanumeric order and appended to your system prompt, giving Cline comprehensive context. 8/ Use this pattern to dramatically improve context management across your team and make Cline more valuable for each specific task.

AI's architectural obsession? Symmetry (with a hint of central command). Blender's MCP server allows you to create 3D worlds using Cline. Check it out now in MCP Marketplace.

"5x force multiplier" How an SF-based sports analytics startup scaled their engineering team with Cline: ?? 1/ Cleat Street faces the classic startup challenge: tight deadlines dictated by sports schedules with limited engineering resources. >Put simply: they need to deliver quality code without expanding their team size. 2/ Introducing AI to your engineering team can be daunting -- they began by introducing Cline for documentation and testing. This approach built confidence while delivering immediate value. Engineers who had never used AI tools could experience quick wins without risking production code. 3/ Key insight: They created a systematic "prompting bank" documenting effective prompts for different scenarios. "The difference between a good prompt and a great prompt can be 3-4x in productivity gains," their Engineering Manager discovered. 4/ The technical breakthrough came when they connected Cline to their entire workflow using custom Model Context Protocol (MCP) integrations. When engineers change API routes, the system automatically updates their Notion documentation through Cline. 5/ Their Linear integration allows engineers to seamlessly move between code and task management without context switching. By reducing these micro-frictions, they've eliminated hours of lost productivity each week. 6/ Implementation detail: They discovered Cline becomes exponentially more effective with similar tasks. Their TypeScript migration, which would have taken weeks, was completed in days because the system learned from each file it processed. 7/ The data proves it works: They're now tackling three major refactoring projects simultaneously with the same team size. $500 in API costs during peak two-week periods is delivering productivity equivalent to 5 additional senior engineers. 8/ Most impressive is how they've maintained code quality: "The last thing you want is people just copy-pasting code without understanding it." Their solution? A review system where Cline proposes changes that engineers approve, ensuring learning and quality control.

Engineers using Cline consistently report completing tasks in a fraction of the time it would normally take. This isn't magic -- it's what happens when frontier AI models can actually see and understand your entire codebase instead of working with limited context. From refactoring projects to documentation to bridging specialized skill gaps, unrestricted AI becomes a genuine force multiplier. The math makes a compelling case: When a single engineer's fully-loaded cost exceeds $150K annually, tools that dramatically boost productivity deliver massive ROI. For teams facing tight deadlines and limited resources, this isn't replacing engineers -- it's amplifying what they can accomplish.

An SF-based sports analytics startup with tight deadlines turned Cline into a "5X force multiplier" that supercharges their engineering team. "Something that used to take two and a half days, I can get that in half a day," says Chrys Propster, Engineering Manager. Their approach: >Start small with documentation tasks >Build a shared prompting knowledge base >Connect Cline to their entire workflow (Linear, Notion, AWS) >Gradually expand to complex refactoring projects The ROI is stunning: $12K/year to amplify each engineer's capabilities 5x, enabling their existing team to handle TypeScript migrations, Tailwind refactoring, and specialized AWS tasks more effectively. It's not about replacing engineers -- it's about giving them leverage to accomplish more with the talent you already have. Read how they did it ??

The hidden cost of most AI coding agents isn't in your subscription—it's in the artificial constraints they put on your models. When AI tools limit context to save tokens, they're optimizing for their margins, not your productivity. A model that can't see your entire file structure can't truly understand your codebase. With Cline, models operate at full potential because we don't limit the amount of context they read or ask for. The economics are compelling: when you can accomplish in hours what used to take days, even premium model costs become trivial compared to the engineer time saved. Don't optimize for cheaper use -- optimize for results.

Mermaid diagrams are the hidden superpower in AI-human communication. They're intuitive for both LLMs to generate and humans to understand, creating a shared visual language that bridges the coding gap. Why does this matter? When working with LLMs, there's usually a translation problem: >You explain what you want in natural language >The AI internally plans complex workflows >You're left wondering "what exactly is it doing?" What makes Cline's implementation so powerful is that it visualizes its planning mode through Mermaid diagrams. This transparency means you can actually SEE how Cline will approach your implementation before it starts. No more black box. No more guessing. Cline thinks through complex processes using Mermaid, showing you a visual map of what it's building. This creates shared understanding that eliminates misalignment. Want to make AI more useful? Give it a visual language both sides understand.

?? Selectable Options are now clickable in Cline 3.7! When building a plan, Cline presents you with choices you can simply click instead of typing out responses. Maintain your flow, and make decisions faster. This small change makes a big difference in how smoothly you interact with Cline throughout your development process.