Chingiz Mammadov

Senior Engineer | 10+ years building real systems (fintech, marketplaces, AI agents) | Practical AI & dev insights from the trenches 🇦🇿 | DM for collabs

[Ori Silver @OriSilver]

We just open-sourced our entire marketing playbook.

After huge viral success with our Marketing OS running on Grok Bot, we decided to bring it to Claude.

Introducing Marketing AGI by Maxfusion.

You no longer need your first 5 marketing hires.

📁 Marketing Department
┃
┣ 📁 Head of Marketing
┃ ┣ 📁 Positioning & Offer Design
┃ ┣ 📁 Pricing Strategy
┃ ┗ 📁 Competitor Teardowns, Public Data Only
┃
┣ 📁 Copywriter
┃ ┣ 📁 20 Variants, Panel-Scored
┃ ┣ 📁 Email Sequences, Written in Full
┃ ┗ 📁 Posts Built to Survive the Feed
┃
┣ 📁 Creative Strategist
┃ ┣ 📁 The 18-Tactic Hook Engine
┃ ┣ 📁 Fatigue Caught at the Concept Level
┃ ┗ 📁 Next Tests, Ranked & Briefed
┃
┣ 📁 Launch Lead
┃ ┣ 📁 The Runway Before Launch Day
┃ ┗ 📁 Product Hunt, Hour by Hour
┃
┣ 📁 GEO Lead
┃ ┣ 📁 Ranked by ChatGPT & Perplexity
┃ ┗ 📁 App Store, Metadata to Screenshots
┃
┗ 📁 Analyst
　 ┣ 📁 Audits, Weighted 0-100
　 ┣ 📁 Numbers That Mean Something
　 ┗ 📁 AI Slop, Caught on Sight

And they coordinate all the work:

A single Claude skill runs the whole loop:

The Analyst finds the problems, the Copywriter rewrites it, the Creative Strategist tests the new version, and the Analyst grades the outcome.

Comment "AGI" and I'll send you the setup.

[Remocn @_remocn]

Introducing Remocn Studio. Waitlist for early access. This is what I've been working on for the past several months. I made every video in Claude Code, and over and over I kept repeating the same thing.

"Why not build myself an app that gets rid of this," I thought

So I built it. Realized it would help a lot of people. This isn't just another AI video editor. There are no timelines, keyframes, or any of the other stuff every editor has. You can't trim a video by clicking on a timeline, you can't manage tracks. All you can do is prompt

Remocn Studio is the director's chair. Here, you direct the people making the video. You watch the process.

"Fix the text here"
"The animation is too fast here"
"Why the f*k did everything break here"

[sunshineLx @ios_1261142602]

最近发现一个好工具

如果你做完iOS App，打算制作宣传视频。推荐一款免费开源工具 👉 https://t.co/TaZP1N6a1w

支持手机壳、精美的背景色、动画、镜头缩放、时间轴线性编辑

对标matte、rotate等 付费产品

[David Mokos @davidmokos_]

I recreated Revolut's tab bar in @expo with all the tiny details

> npx expo install expo-glass-tabs

[Chingiz Mammadov @Chingiz92MI]

@shadcn @davidhdev Interesting. But I would like to see browsers support list🤔

[Kimi.ai @Kimi_Moonshot]

Introducing Kimi K3: Open Frontier Intelligence

🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal
🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts
🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional cost
🔹 Built for long-horizon agentic coding and self-evolving workflows

Kimi K3 is now live on on https://t.co/zrk6zZxZUo, Kimi Work, Kimi Code, and the Kimi API.
Open Weights by July 27, 2026.

🔗 API: https://t.co/XCrgjXAqMw
🔗 Tech blog: https://t.co/YTfiMSNM1f

[Expo @expo]

A bottom tab bar on its own is a solved problem. So is a hamburger drawer. Doing both at once (one nested in the other) is where it gets interesting.

We saw @maazscript building in public and asked him to show how to nest a drawer around a tab navigator with Expo Router, no gesture fights, no tab state resetting.

Full blog below ↓

[Aiden Bai @aidenybai]

HOLY FUCK time travel debugging for React apps thanks to Fable

(with ONLY client side JS, no modifications to the web app itself)

[Chingiz Mammadov @Chingiz92MI]

@_su6an Evel celebrating tactical :)

[Chingiz Mammadov @Chingiz92MI]

@bitforth @AnthropicAI Fixed.

[Chingiz Mammadov @Chingiz92MI]

Finally — AI that collaborates like a real teammate!
Gesturing at the screen, drawing on it, talking live instead of just text chats. Cursor’s Design Mode is making this real. Point, drag, speak → instant UI changes powered by the agent.
Elon gave it 💯 and I see why. Devs are about to move insanely faster.
The era of true human-AI partnership is here. What are you building with it? 👀
@cursor_ai

[Cursor @cursor_ai]

With Design Mode, you can now point, draw, or talk to update your UI.

[Chingiz Mammadov @Chingiz92MI]

Just saw this 🔥 OpenAI dropped “Sites” in Codex!
Turn your ideas, docs, notes, or plans into fully interactive, shareable websites/apps in seconds — and send a simple URL for your team to use.
No-code superpowers just leveled up.
Business & Enterprise users getting it first.
What are you building with this? 👀
#OpenAI #Codex #AI

[OpenAI @OpenAI]

Building apps has never been easier.

With Sites, Codex can turn your work, ideas, and plans into an interactive website or app your team can explore, use, and share with a URL.

Rolling out to Business and Enterprise plans, before expanding more broadly.

[Chingiz Mammadov @Chingiz92MI]

In my opinion, the first thing that an AI assistant should be able to do in any mail client is make all unread mails as read...

[Chingiz Mammadov @Chingiz92MI]

🚀 Cursor just made agents + automations roommates — and it’s a game changer.
No more jumping between separate workspaces. You can now create and manage automations right inside the Agents Window.
The upgrades are 🔥:
•Attach multiple repos to one automation → your agents can reason, code, test, and verify across entire codebases.
•Run repo-less automations (think daily Slack digest that scans unread threads & DMs and tells you what actually needs your attention).
•Tons of ready templates in the marketplace.
And for the next 7 days: 50% off ALL agent runs on every new automation you create. That’s not a discount — that’s “ship it yesterday” pricing.
Cursor isn’t just a code editor anymore. It’s becoming a full AI operations platform.
Download Cursor 3.5 and try it: https://t.co/5J8BgSHqyg
What are you automating first? Multi-repo CI/CD? Personal Slack butler? Or something wilder? Drop your ideas below 👇
#Cursor #AIAgents #Automations #DevTools

[Chingiz Mammadov @Chingiz92MI]

Google just dropped its biggest Search redesign in 25 years at #GoogleIO.
AI-powered search box that reads your mind, smart suggestions, and full multimodal input: text + images + videos + files + open Chrome tabs.
AI Mode, Talk, Create, Camera — all in one clean interface.
Search is evolving fast. 🚀

[Chingiz Mammadov @Chingiz92MI]

🚨 Gemini Omni is LIVE today in the Gemini app!
For Google AI Plus, Pro & Ultra subscribers:
Drop text + images + videos → generate or remix clips conversationally.
Attach from camera roll → “make it cyberpunk”, “add slow-mo action”, “change the background” — done.
Realistic physics, character consistency & smooth edits. No pro skills needed.
Google I/O 2026 cooking 🔥
Who’s generating first? Drop your creations 👇
#GeminiOmni #GoogleAI #AIVideo

[Chingiz Mammadov @Chingiz92MI]

Here’s a ready-to-post X thread:

🧠 Cursor just dropped Composer 2.5 — and it’s seriously impressive.
Built on Moonshot’s open-source Kimi K2.5 with heavy RL tuning (text feedback + 25x more synthetic tasks), this thing crushes long-running workflows and complex instructions.
Benchmarks:
•Terminal-Bench 2.0: 69.3% (basically tied with Opus 4.7 at 69.4%)
•SWE-Bench: 79.8% (vs 80.5%)
Matches the absolute frontier models while being way more cost-efficient. Their fast variant is even cheaper.
As a bonus, they’re doubling usage limits for the next week.
Even bigger news: Cursor is partnering with SpaceXAI to train a much larger model from scratch — 10x the compute on Colossus 2 with a million H100-class GPUs. Future leaps incoming 🚀
Coding just got another massive upgrade.
What are you building with Composer 2.5? 👇

(You can copy-paste this directly — thread format, emoji for engagement, calls to action, and all the key highlights.)
Want a shorter single-post version or a more hype/personal tone? Just say the word!

[Chingiz Mammadov @Chingiz92MI]

🚀 Mind-blowing demo from Google I/O:
Google just had their Antigravity 2.0 agents (powered by Gemini 3.5 Flash) autonomously build a fully functional OS from scratch — kernel, process management, memory management, the works.
No human intervention. Just pure agent orchestration.0
The numbers are insane:
•⏱️ 12 hours
•🤖 93 parallel sub-agents
•🔄 15,000+ model requests
•🧠 2.6 BILLION tokens processed
•💸 Under $1,000 in API costs
Every line of code was generated, audited, and tested by the AI team.13
This isn’t just coding assistance anymore. This is AI building entire software systems like a distributed engineering org.
Antigravity 2.0 is shaping up to be the agent-first IDE we’ve been waiting for.
The future of software development is here — and it’s running in parallel swarms. 🔥
What do you think — game changer or hype? Drop your thoughts 👇
#GoogleIO #Antigravity #Gemini #AI

[Chingiz Mammadov @Chingiz92MI]

Antigravity 2.0 — Next-gen agentic coding platform. AI agents that plan, code, test &amp; even build full apps/OS from prompts. New desktop app, managed agents, coding in AI Mode &amp; crazy demos like building Doom-capable systems on the cheap. Devs eating good bro.

[Chingiz Mammadov @Chingiz92MI]

Here’s more from today’s Google I/O 2026 drops 🔥
#google

[Chingiz Mammadov @Chingiz92MI]

Universal Cart — One smart shopping cart across Search, Gemini, YouTube &amp; Gmail. Tracks deals, price drops, stock, compatibility &amp; more. Agentic shopping done right.