Sabitlenmiş Tweet
Aayush Mathur
117 posts
Aayush Mathur
@Aayush_Mathur7
San Francisco / Singapore Katılım Mayıs 2013
2.5K Takip Edilen316 Takipçiler
I fully reverse-engineered Ramp's internal AI operating system for marketing agencies.
Their system — called Glass — is how they got 99% of their entire company using AI every single day.
350+ reusable workflows.
Every tool connected at first login.
Memory that refreshes every 24 hours.
Automations running while everyone sleeps.
I partnered with my engineering team and we broke down every component inside it.
Then we rebuilt the whole thing for marketing agencies.
76 pages.
Every system.
Every layer.
Every step.
Steal it.
Comment "OS" and I'll send it directly.
Must be a following to receive auto DM
Eric Glyman@eglyman
99% of Ramp uses ai daily. but we noticed most people were stuck — not because the models weren't good enough, but because the setup was too painful and unintuitive for most. terminal configs, mcp servers, everyone figuring it out alone. so we built Glass. every employee gets a fully configured ai workspace on day one — integrations connected via sso, a marketplace of 350+ reusable skills built by colleagues, persistent memory, scheduled automations. when one person on a team figures out a better workflow, everyone on that team gets it and gets more productive. the companies that make every employee effective with ai will compound advantages their competitors can't match. most are waiting for vendors to solve this. we decided to own it.
English
My companies close $20M/year on 30-minute Zoom calls.
I had an ex-McKinsey consultant reverse-engineer exactly how:
– Sales call recordings
– Sales scripts
– Lead gen systems
Reply with “GA” and I'll DM you the copy. Free.
English
The energy in Singapore's builder community right now is unreal. Every team was shipping something genuinely impressive!!
English
3/ Code is disposable now.
I scrapped an entire feature and re-implemented from scratch because the architecture wasn't right. Old me would've spent an hour patching bad code. With Codex doing the implementation, starting over is faster than fixing.
That changes how you make architecture decisions.
English
Won 3rd place at the first OpenAI Codex Hackathon in Singapore!
We built 15 Labs, a multi-agent policy simulator powered by Codex. 🧵👇
OpenAI Developers@OpenAIDevs
We just hosted the first Codex Hackathon in APAC 🇸🇬 Over 100 developers came together in Singapore this weekend and built 50+ projects with Codex in a single day. Here’s what the winners shipped:
English
Aayush Mathur retweetledi
🥉 Multi-agent policy simulator using the Codex App Server where each thread is one agent.
Brian Chew@brianchew
coming in third.. though honestly we're all winners here. access to SOTA models and the support from @OpenAIDevs was incredible ❤️ 🥉 15 Labs by @aayush_mathur7, Zack & Varun what if policy makers could test public reaction before launching a policy? run synthetic focus groups on real questions like GST hikes, transport fare caps, first-home grants and see how different segments would respond before making real decisions. powered by Nvidia AI and AI Singapore's persona dataset. imagine A/B testing policy. that's what this does.
English
Aayush Mathur retweetledi
coming in third.. though honestly we're all winners here. access to SOTA models and the support from @OpenAIDevs was incredible ❤️
🥉 15 Labs by @aayush_mathur7, Zack & Varun
what if policy makers could test public reaction before launching a policy?
run synthetic focus groups on real questions like GST hikes, transport fare caps, first-home grants and see how different segments would respond before making real decisions.
powered by Nvidia AI and AI Singapore's persona dataset. imagine A/B testing policy. that's what this does.
English
I just finished writing my most valuable PDF yet:
"$0 to $10K MRR in 14 days" (19 pages)
It's everything I wish I knew when starting out.
I might charge for this in the future, but for now…
Reply "MRR" and I’ll DM it to you for free (must follow)
English
I want to start a community dedicated to Claude Code.
It’s become the gateway drug to coding and experiencing the power of AI for tons of people.
This will be a space for people to share killer use cases, agentic workflows, proven prompts, and connect with other CC obsessives.
Comment “Claude” if you want to join.
English
English
🎉 Big news! @muppetdev is being acquired by @getsentry!
I'm thrilled to be joining Sentry - their vision aligns perfectly with what I've been building with Muppet, and together we can achieve our goals much faster 🚀
Getting to work alongside @zeeg @madbyk @miguelbetegon (absolute legends!) makes this even better - couldn't ask for a better team to build with!
Bonus: Sentry is incredibly supportive of OSS work, which was huge for me. They're not just okay with my other projects - they actively encourage them!
Super excited and ready to ship more incredible stuff! ⚡
English
used to feel unproductive on my long commutes..
now everytime i step on the muni,
• I create 3-5 tasks (bug fixes/small features) on codex
• review diffs, open PRs if good
• vibe test on staging on my phone
• merge into prod
saves me 4-5 hours a week
English
Aayush Mathur retweetledi
Instantly go from 0 to 1 on any topic with nuggt!
Repo: github.com/shoibloya/nugg…
Link: app.nuggt.io
made with @firecrawl 🔥
English
An underrated way to generate new ideas: Take a slight detour from your daily commute or walk.
Even a small change in route forces your brain to process familiar surroundings through fresh eyes, sparking unexpected connections and insights.
English
@rayyanfkhan Real problem, and those students who are self-learning how to learn with AI will be way ahead of the curve with minimal dependency on educators to guide their learning.
English
embedding AI in education faces two key hurdles:
1) schools prioritize rigid curriculum over the creative agency AI requires
2) teachers lack the AI experience to effectively teach it
don't think 'AI x Education' goes anywhere unless education drastically changes
English