have revolutionized the best way I program. Once I first realized coding again in 2019, I wrote all of the code, character for character. In hindsight, I’m grateful for this expertise, because of the problem-solving mindset coding taught me.
Nevertheless, with AI brokers, I imagine I’m no less than 10x simpler as an engineer than I was. It’s because I’m using AI brokers to carry out as most of the repetitive, mundane duties as doable that I used to need to do. Beforehand, I needed to:
- Manually discover the indentation error in Python
- Carry out lengthy analysis by Googling for solutions
- Carry out giant refactors all manually
And an extended checklist of different duties I don’t spend a lot time doing now. Some would say you shouldn’t let AI do all of the be just right for you, as a result of it makes you a worse coder. I’d counter that AI is just doing the mundane repetitive work, whereas I can carry out essentially the most cognitive-straining duties, organizing and orchestrating the AI brokers.
On this article, I’ll offer you an perception into three of an important strategies I implement to successfully make the most of AI brokers for coding. I imagine these strategies each make me much more environment friendly as an engineer, and it additionally maximizes the potential of AI brokers.
I’m at all times on the lookout for methods to be a simpler engineer, so if in case you have extra options, I’d significantly respect any suggestions!
All through the article, I’ll confer with each Cursor and Claude Code. I’m not sponsored by any of them, and it’s merely the instruments I take advantage of for my agentic coding.
Why it’s best to use AI brokers for coding
I first need to begin off with why it’s best to use AI brokers when coding. The primary argument is that you are able to do extra in much less time.
AI brokers help you do extra, in much less time
Options that used to take 5 hours to implement can now be realistically applied and examined in quarter-hour.
Bugs that took you an hour to determine and half-hour to unravel can now merely be solved by your agent in 5 minutes. With the Linear MCP, you possibly can even simply copy the difficulty URL and have your agent learn the request, discover the error, implement an answer, and create a ready-made PR for you.
That is merely superb. You’ll be able to learn studies on how AI solely will increase effectiveness in 5% of implementations. Nevertheless, for those who begin utilizing agentic coding instruments and the strategies I’m presenting on this article, I’ll assure you see a noticeable change in your productiveness.
I’m pushing code greater than ever earlier than, with out a important enhance in bugs. That’s the literal definition of what makes a programmer simpler.
Method 1: Cursor Planning Mode
The primary and doubtless most vital approach I make the most of is the planning mode every time implementing a brand new characteristic. Planning mode is accessible in all the well-known agentic coding instruments, reminiscent of Claude Code and Cursor. In Cursor, you possibly can choose it by urgent Shift-Tab whereas prompting your agent.
Planning mode makes it so the agent makes a plan for an implementation, both for a brand new characteristic, a bug report, or no matter you need to carry out in your codebase. This plan is made by the agent studying by your request and the code repository with the intention to decide one of the best strategy to unravel your request.
Plan mode then writes the plan to a Markdown file, and would possibly ask you some questions on methods to implement your request:
- Which language would you like the implementation in? Python or TypeScript?
- Ought to the implementation be backwards appropriate?
- Monolith structure, or microservices?
Plan mode is so efficient as a result of pure langauge is inherently ambigoutous
That is the explanation we got here up with a programming language: A chunk of code is deterministic, and at all times outputs the identical, given the identical enter. There is no such thing as a ambiguity in a chunk of Python code, for instance.
Nevertheless, now we’ve reverted to coding by pure language, as a result of the brokers are implementing code as an alternative. Nonetheless, we want an strategy to remove ambiguity, the place the plan mode is available in helpful.
Method 2: Cursor Browser Actions
Cursor browser actions is one other very helpful approach I’ve began actively using recently. Cursor browser actions enable your Cursor agent to carry out actions whereas working in your implementation. These actions could be:
- Open a URL
- Press a button
- Learn console logs
That is an unbelievable instrument to assist the agent resolve one-shot issues, all by itself, as an alternative of you having to manually take a look at implementations within the browser and duplicate console logs containing errors.
As a substitute, you possibly can merely ask Cursor to open the URL, click on round, and ensure there aren’t any points with the implementation. You primarily make Cursor carry out an end-to-end take a look at for you, which is tremendous efficient at discovering challenges in your implementation.
It saves a variety of time to immediate Cursor to open the browser, click on round, and verify the browser logs each time I add a brand new implementation.
Method 3: Examine logs with Claude Code
One other helpful approach I make the most of closely is to verify logs with Claude Code or Cursor.
I take advantage of Claude Code to verify logs in the event that they’re unrelated to an implementation I’m engaged on. For instance, if a doc is immediately caught within the processing pipeline, with out me having modified something within the related code not too long ago.
I take advantage of Cursor usually to verify logs every time I’m engaged on an implementation. I can, for instance, immediate Cursor to ship a take a look at occasion to a Lambda perform, and verify the CloudWatch logs to verify the whole lot was processed as anticipated.
I beforehand spent a variety of time within the AWS console, manually navigating to the related log group and looking out the log group, which takes a very long time. Thus, I began prompting my coding brokers to verify the logs for me as an alternative, which saves me 10-60 minutes per day: an unbelievable effectivity acquire.
Having brokers verify logs is tremendous helpful, and has nearly no draw back. Checking logs is often a easy job that you simply simply need to do. It’s not intellectually difficult or one thing you need to spend time on. Thus, using brokers to scan by logs is an excellent precious use case of coding brokers.
Checking logs is an easy and repetitive job: an ideal job to have coding brokers carry out, whilst you do extra precious work
Should you use brokers to scour by your logs, it’s vital to offer your agent with as a lot background info:
- What are your log teams referred to as
- What are the desk names
- What are the S3 bucket names and prefixes
This protects you a variety of money and time, as a result of your agent doesn’t need to checklist your entire infrastructure as code and discover the related service to look by. I’ve talked about this idea in my article on efficient utilization of AGENTS.md.
Conclusion
On this article, I’ve mentioned three of the principle strategies I take advantage of to successfully make the most of coding brokers. I imagine that using coding brokers and these strategies has made me no less than 10x simpler as an engineer, from an general perspective. It’s revolutionized the best way I work, and saves me unbelievable quantities of time in my day-to-day work. I imagine being efficient at using AI instruments might be extremely vital for the programmers of the longer term.
👉 My Free Sources
🚀 10x Your Engineering with LLMs (Free 3-Day Electronic mail Course)
📚 Get my free Imaginative and prescient Language Fashions e-book
💻 My webinar on Imaginative and prescient Language Fashions
👉 Discover me on socials:
🧑💻 Get in contact
✍️ Medium
