@.h.kmp:

<~H~>🫆313
<~H~>🫆313
Open In TikTok:
Region: SA
Tuesday 21 July 2026 12:45:44 GMT
630
34
1
26

Music

Download

Comments

To see more videos from user @.h.kmp, please go to the Tikwm homepage.

Other Videos

Anthropic just dropped a guide on exactly how to use loops in Claude Code. Think of a loop as an agent repeating cycles of work until a stop condition is met. And there are 4 types, from beginner to fully hands-off. Type 1 is turn-based. This is what most people do already. You prompt, Claude works, you check the result, you prompt again. Every single prompt is technically a loop... you're just the one running it. Type 2 is goal-based. You type /goal and define what done looks like. The example straight from the guide...  get the homepage Lighthouse score to 90 or above, stop after 5 tries. Now Claude can't quit early. Every time it tries to stop, an evaluator model checks the condition and sends it back to work. Type 3 is time-based. /loop reruns a prompt on an interval. Like... every 5 minutes, check my PR, address review comments and fix failing CI. The catch is /loop runs on your computer. Turn it off and it stops. So /schedule moves the loop to the cloud, and it keeps running without you. Type 4 is proactive loops. This is where you combine everything. Schedule a routine to check your feedback channel every hour. Set a goal so it doesn't stop until every bug is triaged and actioned. Use a workflow to explore 3 fixes in parallel and have a judge agent review them. No human needed in real time. One warning from the guide though... not every task needs a complex loop. Start simple, and only level up when the task demands it. I've summarized the whole guide... all 4 loop types, the exact prompts, and how to keep your token usage under control.
Anthropic just dropped a guide on exactly how to use loops in Claude Code. Think of a loop as an agent repeating cycles of work until a stop condition is met. And there are 4 types, from beginner to fully hands-off. Type 1 is turn-based. This is what most people do already. You prompt, Claude works, you check the result, you prompt again. Every single prompt is technically a loop... you're just the one running it. Type 2 is goal-based. You type /goal and define what done looks like. The example straight from the guide... get the homepage Lighthouse score to 90 or above, stop after 5 tries. Now Claude can't quit early. Every time it tries to stop, an evaluator model checks the condition and sends it back to work. Type 3 is time-based. /loop reruns a prompt on an interval. Like... every 5 minutes, check my PR, address review comments and fix failing CI. The catch is /loop runs on your computer. Turn it off and it stops. So /schedule moves the loop to the cloud, and it keeps running without you. Type 4 is proactive loops. This is where you combine everything. Schedule a routine to check your feedback channel every hour. Set a goal so it doesn't stop until every bug is triaged and actioned. Use a workflow to explore 3 fixes in parallel and have a judge agent review them. No human needed in real time. One warning from the guide though... not every task needs a complex loop. Start simple, and only level up when the task demands it. I've summarized the whole guide... all 4 loop types, the exact prompts, and how to keep your token usage under control.

About