like Claude Code can be utilized for all kinds of duties. The primary job you would possibly consider is to truly implement code.
Nevertheless, there are additionally so many different duties that you should use them for. You should utilize them to investigate paperwork, navigate your laptop, use the browser, carry out spreadsheet calculations, and so forth. My level is that coding brokers can principally be used to carry out all duties in your laptop. The duty I’ll cowl immediately is working end-to-end checks with Claude Code.
Finish-to-end checks are principally checks the place you make the coding agent open a browser and click on via it and take a look at its implementations utterly. In that approach, another testing scheme may very well be unit checks or integration checks.
end-to-end checks are nice as a result of they take a look at the appliance similar to how a consumer would use the appliance, which ensures that you’ll be able to correctly take a look at the appliance and uncover points that the consumer would possibly expertise.
Why run end-to-end checks with Claude Code
Initially, I’d prefer to cowl why it is best to care about this matter. The explanation it is best to run end-to-end checks with Claude Code is just that it’s an efficient approach of testing your code implementations. After coding brokers turned extraordinarily highly effective, most notably after the discharge of Claude Opus 4.5, a brand new bottleneck that arose was testing the code that’s been applied.
Earlier than coding brokers, the bottleneck was largely producing the code as a result of it took an engineer a considerable amount of time to supply the code to both implement a bug repair or implement a brand new characteristic. Nevertheless, this has shifted now that now we have coding brokers as a result of they’re so efficient at implementing new code.
The brand new bottleneck now could be principally testing the code. And also you don’t wish to be manually testing all of the code that coding brokers implement, which is why you need to be utilizing end-to-end checks. That is principally making the coding agent totally take a look at its personal code earlier than you confirm the work.
Working end-to-end checks is tremendous highly effective, and it principally offers the fashions a technique to confirm their very own work, which is extraordinarily highly effective and makes them extra prone to do one-shot implementations, which can prevent numerous time as an engineer.
Find out how to run end-to-end checks with Claude Code
Now it’s time to debate tips on how to truly run end-to-end checks. The benefit of coding brokers is that you should use them to additionally arrange end-to-end testing.
Briefly, all you’re gonna do to run end-to-end checks is principally to have a coding agent and provides that coding agent entry to the browser and likewise login entry to the instrument that you just’re testing.
When you’ve performed this, you may merely ask the coding agent to carry out end-to-end checks earlier than contemplating a job is completed. This end-to-end testing is tremendous easy, however there are numerous methods to optimize end-to-end testing each to make it simpler and make the brokers higher at performing the end-to-end testing.
Thus, I’ll cowl some completely different strategies I exploit to run end-to-end testing with Claude Code that make my end-to-end testing simpler.
I’ll additionally talk about some completely different conditions the place you would possibly wish to run end-to-end testing. For instance, you would possibly wish to run it:
- After implementing a brand new characteristic
- after fixing a bug
- on a each day schedule to test that every thing within the utility is working as anticipated
My end-to-end testing immediate
Initially, I’ll cowl the immediate I exploit to carry out end-to-end testing (and, typically, the immediate I exploit to make sure my coding brokers have accomplished their work efficiently).
Implement every thing I requested for. Confirm it finish to finish by clicking via
the browser utilizing the Playwright MCP. It is not acceptable to check the
utility solely via integration checks. It's essential truly click on
across the app. Proceed like this till it really works. Repair any points should you
encounter them then do an finish to finish take a look at once more. Run codex exec and run the
evaluate ability with codex and make him approve it and iterate till codex
has authorized it. When codex has authorized it, get this to dev, after which
take a look at finish to finish in dev once more. Proceed till its working superb in dev.That is the each day immediate I exploit to get stuff to dev. So primarily, I clarify a job to Claude Code. Then I run slash purpose with the immediate that you just see above.
To make it tremendous easy to put in writing out this full immediate each time, I exploit the FluidVoice transcription instrument, and I then say “full merge take a look at”. I then arrange phrase substitute in order that FluidVoice routinely swaps out the three phrases for the total immediate above. This makes it tremendous easy for me to continuously immediate my brokers to run the total end-to-end take a look at.
Playwright MCP
Initially, with Claude Code, they’ve a built-in Chrome MCP you should use to provide Claude entry to Chrome, and it will possibly thus entry the browser. Nevertheless, I personally favor the Playwright MCP as a result of I consider that it makes the agent carry out higher when interacting with the browser. To put in the Playwright MCP, you may merely immediate Claude Code to put in it for you. Restart the Claude Code session, and it’ll have entry to the Playwright MCP, which you should use to work together with the browser.
It’s additionally value noting that there are numerous instruments on the market that you should use to work together with the browser, and that Playwright MCP is just the instrument that I’m utilizing every day.
The /purpose command
The slash purpose command can also be extraordinarily highly effective. Mainly, the slash purpose command is a command that I’ve mentioned earlier than as effectively, however it’s a command the place you set a purpose, and the agent continues till it achieves that purpose. If the agent stops at any level, there’s an computerized hook that triggers, which prompts the agent to investigate if it achieved its purpose. And if it achieved it, it stops, after all, but when it didn’t obtain it, it continues till it achieves its purpose. It’s principally an excellent technique to make the agent proceed working till it reaches a closing goal.
Finish-to-end testing with /purpose is extraordinarily highly effective. The reason being that you should use the command to make sure the agent continues till efficiently implementing what you specify, however it additionally makes it a lot simpler for the agent to confirm its personal work and to make sure it truly achieved the purpose.
Thus, combining end-to-end testing with the command is a really highly effective method that you should use to vastly improve the usefulness and productiveness of your coding brokers
Working end-to-end testing with OpenClaw
The state of affairs I described above is after I run the total end-to-end testing after performing my very own implementations with Claude Code; nonetheless, you may additionally have numerous OpenClaw brokers working. This will additionally make use of the total end-to-end testing.
One particular factor you may arrange is to have an OpenClaw agent set off as soon as a day or a number of occasions a day an end-to-end take a look at of your manufacturing utility. This testing ought to undergo all the utility, use the completely different options, and ensure all of them work as anticipated, which can provide help to uncover numerous bugs.
Since you set off this on a schedule, you’ll discover numerous bugs earlier than customers uncover them, which is after all one thing it is best to at all times attempt for.
You too can set this up utilizing a cron job in your laptop or the schedule performance in Claude Code. Nevertheless, I discovered that organising an OpenClaw agent to carry out this end-to-end testing works very effectively. It could actually replace the testing scheme each time I replace the appliance and routinely repair the problems that the OpenClaw agent discovers.
Conclusion
On this article, I mentioned how one can run full end-to-end testing. That is principally a method the place you make a coding agent undergo the browser to check the implementations that it implements. Finish-to-end testing is extraordinarily highly effective as a result of it experiences the appliance similar to a consumer would, and it thus helps you uncover numerous bugs. I consider end-to-end testing and, typically, verifiability is extraordinarily vital relating to making probably the most out of coding brokers, and it’s one thing it is best to at all times arrange in order that it’s easy on your coding agent to run full end-to-end checks. You also needs to set them up on a schedule so that you just uncover points earlier than your customers do.
👉 My free eBook and Webinar:
🚀 10x Your Engineering with LLMs (Free 3-Day E-mail Course)
📚 Get my free Imaginative and prescient Language Fashions e book
💻 My webinar on Imaginative and prescient Language Fashions
👉 Discover me on socials:
💌 Substack
