Zoaib Khan

✨ Angular Agentic Coding: The Process in short! It's basically a three step process - but with sub steps within it. The green part (testing) actually ensures your code quality is upto the mark. Check out the complete video here: buff.ly/EKOna6z

✨ Angular + Cursor 3 = automated testing with Browser! Here's me asking an AI agent to test the CRUD flow on my feature and verify it works. Pretty neat! Full video where I build this Angular Products table: buff.ly/EKOna6z

Mental note: try out HTML while planning a feature!

📽️ And the video is out! Agentic Coding Workflow for Angular developers - check it out 👇 youtu.be/U_0UibgryFI

VS Code also going the way of Cursor 3 - and all the other agentic coding tools

⏳ Currently recording a real agentic coding session for Angular developers! I'm building a CRUD feature in my Angular Dashboard - and the tutorial will be a sort of unfiltered view into the process that follow for my development nowadays. Subscribe youtube.com/ZoaibKhan

✨ Added a standard CRUD flow today on the Angular Dashboard! BUT I used an agentic coding process - grill me, implementation plan, browser auto test, code review skill for standards/architecture, manual review Will show in a video soon Subscribe: buff.ly/X2SxPXl

@leerob That is so true, I've been trying to create and test a code review skill to spot architecture and other code issues in my Angular code - though it does get me about 70% there, there are still some things which slip through. Need review even if an overall skim of the code!

Code is actually the right abstraction. Too often I see the future of software engineering diminished down to, effectively, writing and reviewing markdown files. Yes, it will be hard to review thousands of lines of agent code. But maybe the takeaway is that you want less code? Rather than just giving up ("well I guess we won't read the code, or we'll read this lossy markdown summary") this should be a signal forcing you to think about better systems. - How can we make our codebase more verifiable? For example, fast/robust/stable tests, or moving to a typed language. - How can we deslop or improve the architecture/abstractions of the code generated by agents? For example, spending more time up front on the codebase architecture/types before yolo generating all of the code. - How are we going to maintain and evolve this codebase over time? The slop compounds. One great solution here is... you guessed it, learning from the past decades of software engineering! For example, you might just have the wrong abstraction entirely, leading to a ton of duplicated code. I think the markdown folks *are* right in some ways. If you are using skills every day, for many different prompts and workflows, isn't that effectively "coding with markdown"? Kinda. There's been plenty of ink spilled on the merits and benefits of skills. To me, skills make your style of working legible for agents. They don't replace code and that's not really the point. In reality, there's this messy and constantly re-evolving future in which both of these things are true: 1. Skills (and markdown) are important for how you give input to the agents and ensure high-quality code & systems are created 2. Looking at the actual code will not be replaced by markdown summaries or a collection of spec documents that ignore the lower level details of the code In summary: reality has a surprising amount of detail (and nuance)!

@codewithantonio same here, it's remarkable how the workflow has changed in the past few months

i have been using my IDE only as diff viewer for the past few months, wild times

✨ Cooking something for the Material Theme Builder! Ready made material theme presets for common use cases - such as SaaS Dashboards or Fintech products etc. It's not quite there yet - but soon :) Btw, if you're struggling with mat theming, do try materialthemebuilder.com!

P.S. I have been using Cursor 3, the newer agent based version of Cursor. And I've come to love it now.

Till now, I've been using GPT/Opus for Planning, but Composer 2 for everything else. And it has worked kind of ok. But it seems I'll have to go for expensive models for the code review pass as well

I created my own code review skill recently to catch architecture and other problems in my Angular code. Ran it today on a complex feature and apparently models really matter a lot here. Composer 2 couldn't catch much, GPT 5.5 did a pretty good job!

✨ So I finally tried the grill me skill by @mattpocockuk when adding a feature to the Material Theme Builder! It asked me 16 questions - it was hard BUT it helped me a lot in understanding the feature - which should help in translating it into a not so buggy implementation :)

@addyosmani It's an interesting suggestion. I'd love more human readable plans as well, long plans in markdown are pretty difficult to read, no doubt. I think this will be esp useful for front development

Move from Markdown to HTML and give AI a richer canvas to communicate output humans will actually read. Think plans, specs even throwaway editors. Like this idea which keeps more humans in the loop.

✨ The thing about Agentic Coding is that it gives you possibilities that you did not think of before... Yesterday I added drag and drop resize to the widgets in my Angular Dashboard project - complete with tests. It isn't perfect, but works well.

@housecor In Cursor 3, there is a design mode where we can do exactly this! I love using that to pinpoint UI changes

Problem: How do I quickly tell AI exactly which elements I want to change? Solution: Agentation This npm package displays a toolbar in your app so you can click on elements, add comments, and then send those comments to your LLM (like Claude Code).

Oh this should be very useful in context management

✨ The two traps we can fall into when using AI agents to code! The vibe coding one is obvious, but the over controlling one is also an issue I feel. Full video: buff.ly/Vry5CHe

✨ Years of writing (or trying to write) clean Angular code. Then I tried AI agents and my own instincts worked against me. New video on the mindset shift every experienced dev needs for agentic coding. 🎥 youtu.be/1mlHpuuo_Hk