Mohammed Junaid

Hey @nikitabier, is X A/B testing football scores on me? 😭 1–0 → 1–1 → 1–0

Notion is quietly pulling off one of the biggest pivots in SaaS. Note-taking app → developer platform. In 6 months: → Custom Agents (1M+ built already) → Workers: run your code on their infra, no servers → A CLI designed for coding agents, not humans → Claude Code, Cursor & Codex now work inside your workspace → Killed Notion Mail to double down on agents They don’t want to be your docs app anymore. They want to be the OS where humans and AI agents work together.

This is the team workflow I want to see more of: end the day with specs and acceptance criteria, schedule agent work after 22:00 Beijing time, wake up to PRs and reports, thenreview with a fresh brain. Qoder's discount makes the expensive part, long autonomous execution, cheap enough to run every night.

@MrAhmadAwais @CommandCodeAI This is huge! Congrats Ahmad!

BIG day for us!! @CommandCodeAI has crossed $1M in annual run rate, 1 trillion tokens of usage, with over 9K customers, just 24 days after our public beta launch. we believe this makes it the fastest-growing coding agent harness for open models. 3rd largest by usage. Command Code is built around two ideas: 1. open models should be production-grade for coding. 2. your coding agent should learn your taste. we're building for taste and developer experience. so instead of making a soup of thousands of models, we build for the best ones, open or closed. the goal: a coding agent that feels like an iphone, opinionated and with taste, not a random android or a windows phone with no taste. on the first idea: open models. we fixed the "open models aren't good enough at tool calling" problem. our research came down to two things, quality and speed, and both trace back to one root cause: broken tool-calls that open models produce, especially when you use a bad harness. open-model tool-call failures are not deep, they are a small finite set of contract mismatches. so we repair them, with zero token loss. what started as 4 repairs is now the largest repair layer in the space: 36k tool-call fix variants. i wrote the idea up openly¹ a few weeks ago, and it has quietly become a de facto way people fix open models. developers have either adopted Command Code or used the same idea to build repair harnesses for nearly every top coding agent. i take that as more meaningful validation than anything we could say about ourselves. on the second idea: taste. Command Code builds your coding taste into skills, learned from your accepts, rejects, edits, prompts, and the corrections you repeat. over time it drifts away from generic code and toward how you actually ship code. it learns continuously, and while it is early, the direction feels right. net effect: developers using Command are writing production-quality code on open models, 10x to 100x cheaper, without fighting tool calls, while building repo and team-wide coding taste that compounds. i believe these numbers are a consequence of getting those two things right. what's next. we've applied the same repair idea to ai design slop, and bundled a /design capability² so every developer can level up their design work. the early response has been great. we have a big roadmap ahead of us. the feedback we hear most is that Command Code feels fundamentally different: an approach built on taste and repair. we're going open source next month. today we're a cli at the core, and we're also launching a full-fledged gui app, sandboxed background agents, and cooking up something fun i can't wait to share. we're growing too, hiring in sf and remote worldwide. check open roles on my profile bio. try it now. npm i -g command-code if you like engineering deep dives on how we're doing all this, i've linked some relevant posts below.

@arjun_gupta95 🙏

@mdjunaidap Great job 🚀

Launching Buildmap 🚀 A spec-driven planning workspace for AI-assisted builders. Turn a rough idea into: PRD → Architecture → Feature specs → Context files → AI coding prompts → Shippable chunks. Built during the OpenAI x Outskill AI Builders Hackathon. Better specs. Better AI context. Cleaner builds. Visit now: buildmap.live #Outskill #OpenAI #Codex #AIBuildersHackathon

@mehulmpt Cool, best of luck. Mehul!

Earlier this week, I left Bangalore/India, moved to Dubai indefinitely. I can add reasons but I will skip because internet loves to lose nuance. I also considered SF/US as an option but passed on it for some other reasons. Dubai, UAE is what I hope would be my new home. 🇦🇪

Let’s understand AI latency in 5 quick tweets. Why some AI apps feel instant while others feel painfully slow:

Claude dropped 4.8 and suddenly even 4.7 feels like a limited edition model 😭 Me: sends 3 prompts Rate limit: “That’s enough innovation for today.”

Follow @mdjunaidap for more

The best AI products balance: speed + quality + cost That’s the real challenge.

Let’s understand retrieval systems in 5 quick tweets. This is how AI gets access to knowledge beyond training

Follow @mdjunaidap for more

Without retrieval: AI guesses. With retrieval: AI becomes grounded in real data.