Was recently preparing for an important meeting and had grok bot live audio grill me with questions and judge my answers as I have them.
@bot is seriously brilliant, although maybe an Aussie accent would be helpful. Please....
Also had it review the transcript from the session and grade em for gaps, things I could have done better or did well etc.
This type of coaching / feedback would have been so helpful back in school.
El Combo retweeted
We find the users who send the majority of their messages in projects merge 6x more PRs vs non-projects users.
Projects also helped teach me to delegate and validate the same way @bot does
Honestly if you're not using @cursor_ai Projects you're just missing a ton at this point. Don't sleep on it. Give it a try and see how it significantly improves your life. Here are some tips for you. I'm using it since it was debuted internally:
* Have a single `Hub` that acts like a office manager. Use it for best practices, ask it to investigate how each project is working, what's missing? What can be done better? It there to help you and getter better
* Start with a few projects first, don't overdo. With time you'll understand how many is enough. For example I recently started a debug session for some of our Cloud Agent nodes, I knew I was going to create multiple agents, review agents and so on. So I created a single Project just for this purpose
* Make sure to use a proper model. Grok 4.7 is pretty good do the Project coordination part. I also use it for all kind of chores. If I need a big hammer, it dispatches agents with Opus/Fable. Cursor is nice because you're not bound to a single model!
* Give more autonomy to your coordinators. Share that you "don't want to be bothered" , ask upfront if there are any MCP logins, or website auths needed for the work to be done. Remove all self inflicted blocking, and then let it rip.
* You can assign nice icons and colors, choose them deliberately, it'll help during context switching.
* Enable remote workers. By default Projects runs in Cloud Agents, but suppose there is something to be done that can be only on your localhost, the coordinator can dispatch an agent that runs in your machine.
For more details read cursor.com/blog/projects and also my blog post arslan.io/2026/09/11/how-i-m…
El Combo retweeted
We're seeing significant improvements with our new inline common chunks feature! It's substantially reducing the number of small chunks in some of our internal projects.
We're still refining it, but we've put together an in-depth guide explaining how it works:
rolldown.rs/in-depth/inline-…
Everyone is trying to get their x-stack AI skills, no one seems to be taking the time to use the word 'stack' suffix well.
Smokestack or haystack would fine choices. Even some dad jokes or puns would work!
El Combo retweeted
Google Docs now has native Markdown support 🎉
developers.googleblog.com/pr…
El Combo retweeted
An 86-minute guide to finding product-market fit
Rob Snyder (@RobSnyder1) is the author of The Power of Pull, has helped over 50 startups go from zero to $1M+ ARR, and is the most requested guest by my podcast listeners.
We discuss:
🔸 The PULL framework for finding a customer who’s "weird not to buy"
🔸 Where the best startup ideas come from
🔸 The cold outreach message that gets calls
🔸 How to run your first sales call (and why he skips design partners)
🔸 The "Hail Mary" question and "goblin mode"
Listen now 👇
youtu.be/19qrLchbQEc
El Combo retweeted
json-render v0.21.3
→ Reliable YAML patch operations
→ Safer JSON Pointer path handling
→ Fixes for repeated streaming operations
→ Improved chat example styling
→ Better shadcn skill compatibility
→ Updated docs and examples
Big thanks to @mdlahfir, @BTCOrangeCoin, @\dajiaohuang, @\Jassi2004, @\xiehuanyi, @\kevin9327, @\adhamali450, @\monsterlag
github.com/vercel-labs/json-…
El Combo retweeted
i've been a bit quiet - working on a new companion skill that will help your agents draw these beautiful statecharts/diagrams + check them against the specs you made with /create-formal-verification-skill in pstack!
it now uses Pele from @kepano too which is why they look so good.
will release soon!
there's something really cool about asking your agent to draw a statechart (hypothetical example in this image), then using the /create-formal-verification-skill you made with pstack to find bugs through something like TLA+. you can both understand your code better and how the user flow should work, and fix issues users would otherwise see
El Combo retweeted
I reworked the Hex homepage for no reason 😅
Try it out for all your speech to text needs. It's free, multi-platform, and pretty good.
Also, I just added added faster Parakeet streaming models, so dictation's even faster now.
Why are GitHub stacks so awful. I had an agent create a stack of 12 prs to keep them small, reviewable etc.
I had each reviewed and had to update them based on review comments.
That created a cascade failure of running all other prs in the stack and soaked up all the shared GitHub runners for the team.
I'm sure it was a skill issue, but man some rough edges burning money and runner credits isn't fun. Definitely don't have GH configured to rerun all prs in a restack.
El Combo retweeted
How do you _guarantee_ your agent's code is correct? You prove it.
Introducing Proof Driven Development Kit (PDD Kit) from @MSFTResearch.
PDD Kit helps turn your plan into a formal spec, then proves the agent's code meets that spec for every input. No vibe verification. PDD Kit is integrated with @GitHubNext's Chopin, so you can plan as a team.
PDD Kit takes an app's login flow from intent to a verified pull request:
It discusses your code, infers your intent as it goes, and proposes a formal spec in Verus, a proof language for Rust.
Once you approve the spec, the Verus verifier automatically proves the code meets it.
Where proof isn't possible, it falls back to empirical verification with tests and computer-use agents (CUAs).
It works on Rust today. No new language, no change in how you produce the underlying code, making formal methods more accessible.
The goal is a verified software factory, where engineers review specifications instead of code.
Come see it in action at GitHub Universe, Oct 28–29. Swing by the Speakeasy and ask for GitHub Next!
El Combo retweeted
tried tsrs on an app of mine (~190k loc). looks promising.
Introducing tsrs: a Rust port of the TypeScript compiler 🦀
We are not forking TypeScript!
◆ In close collaborating with the TypeScript team
◆ Up to 8x faster than TS 7.0 & ~70% less memory
◆ Runs in WASM, so it works in your browser & on Workers
◆ Soon part of the Oxc toolchain
npx tsrs
blog.cloudflare.com/typescri…
El Combo retweeted
Make sure you are auditing your tests in your repo that your agents have written. You'll be shocked at how bad (or even useless) they can be, especially as they stack on top of previous agent work.
Compound Engineering makes it easy:
"/compound-engineering:ce-simplify-code do a test audit of this repo"
Ran it in a new repo i'm working on for the first time, result:
El Combo retweeted
Diagram Design turns prompts, draw.io and Mermaid sources into editorial technical diagrams.
It ships 27 visual types, brand onboarding, and HTML/SVG/PNG export.
Works with Claude Code, Codex and Pi. MIT licensed.
github.com/cathrynlavery/dia…
ALT Source screenshot from Cathryn Lavery's Diagram Design repository showing an editorial redraw of a software architecture from a draw.io file. Web App and Mobile App send HTTPS requests to an API Gateway. The gateway verifies requests with an Auth Service and routes orders to an Orders Service. Orders are stored in Postgres, while asynchronous paths archive to an Object Store and cache sessions in Redis. Solid blue lines mark HTTP calls; dashed lines mark asynchronous work.
