Jun 5 • General discussion 💬
⚡️ Anthropic just told the market that more than 80% of the code going into Claude is now written by Claude itself...
It came out the same week they filed for IPO, so it's not a throwaway line. That's their actual development process.
Forget the stat for a second. The useful part is that you can copy the setup behind it. Here's what makes Claude write the majority of your code well, instead of slop you have to babysit.
1. Plan before it writes a line.
Don't ask for the feature. Ask for the plan first. Get it to lay out the files it'll touch and the approach, read it, correct it, then let it build. Most bad output comes from skipping this step.
2. Give it the context it needs.
Claude writes badly when it's guessing. Point it at the actual files, the docs, the example you want it to match. The more relevant context in the window, the less it invents.
3. Make it check its own work.
Have it write a test, run it, and fix what fails before it hands anything back. This one loop is the difference between code that looks right and code that actually runs.
That's the whole game. Plan, context, verify. Same loop Anthropic runs internally, just smaller.
Try it on one task this week. Pick something you'd normally write yourself, make Claude plan it first, and see how much further it gets.
What's the biggest thing stopping Claude from writing good code for you right now? Drop it below.
1
0 comments
⚡️ Anthropic just told the market that more than 80% of the code going into Claude is now written by Claude itself...
powered by
skool.com/automation-forge-7306
A community for mastering AI-driven automation and AI agents.
🧰 Work with Me
📩 Join the Newsletter
⏱️ Waitlist For Paid Community
Suggested communities
Powered by