Pinned Tweet
Agentic Angular is live 🚀
As software engineers, our way of working is changing. Our role is shifting from writing code by hand to managing AI agents.
I've spent the past year or so figuring out how to make that shift on real projects. This course is my attempt to help you make it too.
Out of the box, agents have real problems: hallucinated or outdated APIs, over-engineering, code that drifts from your standards. The answer isn't a better prompt. It's a better process:
→ Specify every feature in each loop: grill, plan, implement in a fresh agent, review.
→ Set architecture and standards once and enforce them automatically. Tests, lint rules and type checks do a lot of that work.
It's practical and hands-on. Step by step in Cursor, we build Tint 3D, a real Angular app with Firebase and Stripe.
What you get:
• Module 1 live now (12 lessons), new lessons every week
• Every future lesson and module included
• 2 private GitHub repos: the finished app + the one we build
• Course support by email
• 30-day full refund, no questions asked
Early access is $99 (regular $199). No countdown, but the price goes up as new modules land.
Join now (early access): zoaibkhan.com/agentic-angula…
Trailer: youtu.be/_6fYqzONmAM
1
1
168
This is my experience as well with @bot - it's a whole new level of productivity.
Being a parent, it's particularly useful because you can kick off and check work in between parenting errands. You no longer have to be locked to your laptop to do meaningful work!
BUT there is a tradeoff. Being so easy to access and work all the time, it can get hard to maintain work life boundaries. That's a challenge for this mode of work
33
Using one Cursor Project + @bot for my upcoming "Agentic Angular" course has made everything much simpler.
No need any more to refer to specific chats or past conversations to get context about different decisions I've made leading up to the course launch.
Instead, the Cursor Project has a handy notes area referring to all of this rich context and @bot can simply be asked to look it up and get all of the stuff I've already done for the course.
It can reason better and give me better suggestions about future plan or marketing content for it - because it has all of the context!
I'm loving it 🔥
1
209
Yesterday, I used Grok bot for editing a large lesson of my upcoming "Agentic Angular" course.
And it was as easy as asking it to connect to Descript using the Descript MCP.
I could then easily ask it to create a cut based on my preferences in a new composition in my project.
And it did a pretty good job - speeding up the workflow.
@bot helps me out everyday in different areas of work - it is so handy!
1
127
I've been doing "Grok-@bot driven development" for some time now. And slowly warming up to the whole idea of cloud based agents.
I love that I can fire off and verify work from anywhere - it is very freeing, especially for parents who are working in between parenting errands!
One fear though - I'm beginning to see me working everywhere. Will need to establish some boundaries like not to check the bot after certain hours.
But overall, I'm enjoying this way of working
54
I like the Michelin kitchen term better, by @poteto
major vibe shift re: the software factory in October. everyone I know who resisted this idea is now building one.
1
118
This is true, programming fundamentals matter, but specific syntax is becoming less and less important.
If you understand code, you can spot-check most languages — even if you don’t know them. Mid and high level structure are pretty obvious in virtually all languages. Names are self-evident.
The captain knows how the ship works at a high level. He does not know the torque rating of every bolt.
67
I've trying lint rules for code problems in my Angular projects as well - and I'm surprised the agent can come up with pretty good deterministic rules for most coding standards.
Sometimes they overdo it - but it allows you reframe your rules as well!
Replying to @poteto
trivia:
• started working on the game as a side project 4 days ago, landing ~1,150 PRs
• every time i found an issue in the code i asked bot to make a lint rule against it
• used TLA+ heavily to find bugs in the game's various state machines: the story, cutscenes, the game's systems. there are many formal verification skills, one for each major system
• i put context into the filepaths: code that runs every frame or every tick gets a .hot.ts extension, and a lint rule bans allocating in it (no object literals, closures, new, etc.), so the game loop creates almost no garbage and GC doesn't cause stutters
• game engine is mostly custom. three.js draws the 3D scene, but the simulation, post-processing and audio are all ours
• the simulation is fully deterministic, so every run replays exactly from its inputs. when you post a high score, the server replays your whole run to check it isn't cheated
• we generate dynamic og:images for every run based on your final stats, and it's all localized too! the game supports 10 languages
• my favorite feature: the music seamlessly transitions into different music for the various biomes, continuing the previous melody
• no audio files. all the music and sound effects are synthesized live in the browser by a custom Game Boy-style chip (two pulse voices, a wave voice, noise) plus a synthwave layer. the songs are written as text in code
• all the pixel art is code. every sprite is a file drawn with one shared palette and packed into a sprite atlas at build time
• it runs inside an X post, from the 245px card up to full screen. the bar is 60 fps with 500 enemies on a mid-range phone
• the build fails if the first download goes over budget. it's about 124 KB gzipped right now
• bots play the game headless to tune each difficulty against target survival rates
• comments are banned by a lint rule. if code needs explaining, the fix is a better name or a test
77
Zoaib Khan retweeted
Moved to Angular Material v19+ and color="warn" stopped working on your buttons?
M3 swapped warn and accent for color roles. Point the button's tokens at error or tertiary and it follows light and dark mode on its own.
See every button token live: materialthemebuilder.com/bui…
For Angular, I'm using the ngrx signal store for all my projects. And having lint rules for thin components tends to shift almost everything to those stores.
Maybe Redux, or a Redux-like framework needs a comeback
Having state in ONLY ONE PLACE sounds pretty beneficial to agents
I.e. restrict the decision space, only allow one way of doing things
1
87
Material Theme Builder has its own account now: @MatThemeBuilder
That's where I'll share new themes, quick walkthroughs like this one, and tips for theming Angular Material.
If you build with Angular Material, give it a follow 👇
Ever wondered which token is actually styling an Angular Material component?
Turn on inspect mode, click anything in the preview, and see every token behind it. Click a role to jump straight to it and edit it live.
materialthemebuilder.com/bui…
90
Courses focusing on language syntax and manual coding won't work now - simply because there is less interest in that - and for good reason.
There is a lot of confusion though for those transitioning from manual coding to agentic coding. Because it's such as mindset shift.
I'll be launching my own little effort soon to address this - which I'm calling "Agentic Angular".
We'll build a whole product from scratch using the agentic process! More info soon :)
An alternate data point. This has been my best year selling self-paced video courses, which has been 98% of my income since 2022.
A great course reorients the learner in the world. It doesn't just give them new knowledge, it makes new things possible.
Also, course creation is curation. It takes a spread-out graph of information, finds the most impactful nodes, and linearises it. This means courses are fast-tracks - they get you to where you need to go faster.
So, in the AI world, what is worth learning?
For me, that has meant finding techniques which are:
- Harness-agnostic
- Model-agnostic
- Language-agnostic
...that benefit the agent and increase output quality. Because they're everything-agnostic, you can drop into any codebase and succeed.
This is a huge space. I've explored a small part of it: software fundamentals, module design, increasing test quality.
But there is SO much more there. User interfaces, company process, leadership, observability, product design.
But you've got to make the right course. I wouldn't make my "Total TypeScript" course now (sales have dropped off a cliff). That one focuses too much on API's, learning language features, aspects which are easy to ask agents about.
Instead, I'd make "TypeScript for AI", focusing on the actual things you need to know to make a productive TS codebase for agents (and it would rock, too).
It boggles my mind when people say courses are dead. The hunger for information is very much alive. Go feed it.
1
3
111
I like Cursor's design mode for this, but for it to be fast, the model has to be fast as well. I'd love to be able to batch tweaks though in one go - since I usually want to tweak multiple things at the same time
Still find prompting UI tweaks to be way too slow compared to direct manipulation like in a design tool.
What's your work flow for fine-tuning UI details in code without being the victim of the brutal agent feedback loop?
1
124
codebases have always contained slop. we have always been okay with this because code rarely needs to be perfect, outside of mission critical "hard" (eg embedded) software.
swe is a unique form of engineering because you're often building something that constantly evolves and is almost organic - user tastes change, your mental models evolve, and features come and go.
admittedly, i and many others who've been coding for a long time were initially (like back in 2024) skeptical that agents would write production code. "but what about all the slop that would enter our beautiful codebase?".
well, even before, we had human slop, and there was a lot of it! if we're being truthful, most people call "code i didn't write" slop. the reality is that 99% of people (i include myself in that number) don't even know what Good Code looks like, let alone be capable of writing it. i would propose that Good Code is:
• correct
• bug free
• fast and cost efficient to run
it has always been exceedingly difficult and expensive to write truly Good Code, because for the longest time (maybe @bendlang will change that), code was not something you could cheaply and formally guarantee to have all 3 of these properties. this is why writing hard software is much more difficult and expensive, because depending on the use case, you may only get one chance and so you have to be right from the start.
but the vast majority of software we use does not need to be Good Code to provide value to users. in fact, it is very likely that most software we use is not formally verifiable! we accepted some bugs in exchange for velocity and progress, so we rely on tests and o11y instead and have adopted a more incremental approach. this is a good thing!
agents help us move faster, and if you're open to the idea, are capable of helping us write better code. it won't be Good Code (that is still expensive), but it is likely to be much better on average at scale.
the new craft of swe is to figure out how to do this. it's your job now! if your productivity with and without agents is not significantly different, you're doing something wrong. but it's not too late to embrace it and use it as an opportunity to learn a whole new skill tree
Zoaib Khan retweeted
Instructions are a last resort.
Want to enforce a coding standard? Configure or create linting rules.
Want to avoid the LLM copying an existing anti-pattern? Refactor the bad pattern and make it a build error if it happens again.
Want to explain a confusing or insistent design? Fix the design and be consistent (it’s easier than ever with AI!)
Want to run a process after each file edit or when the model stops? Use a hook.
Want to describe a process like opening a PR or doing a code review? Create a skill.
Instructions are rarely the best option.
They’re “soft”.
They bloat context.
They’re often ignored.
And they often paper over problems.
Fix the root causes. Use deterministic tools.
Each time I see the agent make a mistake I ask, “how can I make this mistake impossible?”
Instructions are just a suggestion. The techniques above create *certainty*.
That’s why instructions are a last resort.
I have the same sentiment. While models might not be there yet, but they will eventually from the trajectory.
We're finding ourselves moving up the abstraction ladder bit by bit every day and it can be disorienting.
I try to focus on the new possibilities that offsets this doom
Replying to @ThePrimeagen
I've been reflecting on this. I'm generally a very optimistic person, but lately I've been feeling a strange sense of sadness that coding has been "solved".
I can, and have, made many caveats to "solved"... but I also know that in five years none of them will matter. It will be solved.
Building things is still fun, but a different kind of fun. It doesn't activate the same parts of my brain as trad coding did.
I think it's okay to mourn the thing we loved doing being different now. Software was the first job to go through the five AI stages of grief, which means we're also some of the first to internalize that this will happen to many other jobs.
It was the best of times, it was the worst of times.
1
126
New Grok @Bot features!
Here's what's new in Grok @Bot this week
0:08 Voice calls and voice memos
0:35 1Password vault for Grok Bot
0:53 Inline forms
1:07 Inline drafts for email and Slack
1:31 Account switching
1:40 Route traffic through your desktop
What's new in Grok Bot - Sept 23, 2026
What's new in Grok Bot - Sept 23, 2026
I don't use the "official" plan mode myself, but I do come up with an implementation plan based on grilling session and coding standards.
That has been enough for me
we’re thinking of killing plan mode and using the shift+tab hotkey to adjust effort levels
I don’t think the models need plan mode anymore, but if you’re a plan mode diehard would love to get your feedback on why
1
111
Mental note: Use this on the material theme builder.
I find the latest models write a lot of unit tests. Most of them restate the code they were written after, so they always pass and catch almost nothing. They run fast, but they break on every refactor and the agent burns time fixing tests instead of the feature.
The prompt I used to clean out mine, adopted from Ansh is:
"This repo is full of low-signal unit tests. Delete every one that wouldn't catch a real bug our E2E tests miss. Fan the work out across parallel subagents.
Then add these rules to AGENTS.md so future agents stop writing them.
- Never write unit tests after you write code.
- Highly prefer E2E tests as the sole testing mechanism. Use them to verify complex features work. At the end of E2E tests, produce a verifiable and repeatable artifact.
- If you must test a system in isolation, first write down all the ways it could fail, then write the code."
95





















