Co-Founder @SuperKalam_ | YC W23 | BITS Pilani | Writing about building with AI
Bangalore, India
Joined June 2020
- Tweets284
- Following1.1K
- Followers352
- Likes1.8K
Pinned Tweet
Wrote the script while waiting for food
Three of us acted and shot it
Claude edited it overnight
Focus was on peak detailing
Inspired by @RanveerOfficial @AdityaDharFilms
We couldn't afford @RanveerOfficial & @AdityaDharFilms, so we made Dhurandhar ourselves - ft. Startup Hiring
Got 113 applications in 2 days for the Product Designer role at @SuperKalam_ .
I will use AI to analyse and shortlist candidates based on a few parameters.
While doing this, I realised something:
Just like SEO / AEO / GEO, portfolios need to be LLM-optimised too.
A portfolio thats easier for an LLM to read could get evaluated more accurately and thoroughly.
Before a human opens your portfolio, an LLM might have already analysed your projects, skills, and experience in depth.
Soon, portfolios will need to impress both humans and AI.
Crazzzyyyy!
🤖 Made with AI
We're hiring Product Designers at @SuperKalam_
📍 HSR Layout, Bangalore
Make sure your work is as exciting as your Framer template
📽️ Check video for details
🔗 JD link is in the comments
🫡 Special shoutout to @vimal8rathore , who used Claude Code to edit this video.
Apply here - ycombinator.com/companies/su…
The more I use AI heavily at work, the more I realise that even AI agents need onboarding, just like humans.
Initially, building fast with AI excites you. You get so many ideas to implement, and suddenly all of them seem possible.
Then comes the frustration. You have to wait for AI to make the first iteration, focus on small nitty-gritties, and keep fixing things.
The real shift happens once you understand:
- What systems need to be built with AI
- Where AI can make better decisions
- What needs AI-assist and what can be AI-native
Once you figure these out, you will be able to pull off much more than you thought earlier.
Even AI agents need proper onboarding like humans.
Better onboarding gives them a better head start.
Growth is a weird function of creative inputs producing objective metrics as outputs.
And the zeal to shamelessly execute every idea you believe in is what keeps growth alive, day after day.
Startups are built with relentlessness.
They are not sprints. They are marathons.
And the hardest part of a marathon isn't the start or the finish.
It's everything in between.
#LFG
This is what I send my friends when they connect their Instincts with mine.
Great product @noahrshinn 🙌
"Sophisticated engineers" fighting over a matching symbol on a card at the @SuperKalam_ office inauguration.
Including me :P
New SuperKalam home :)
3x bigger than our previous office.
We wanted trees around us, room to work, talk, build, play, and spend a lot of time together.
After months of searching, we found it.
This is the kind of place we wanted to build @SuperKalam_ & @heyhomiapp from.
Let’s build.
Building AI-native products using agents, agentic workflows, LLM orchestration, and human-in-the-loop pipelines. Quite interesting.
Amazing article - Discipline Comes from Having No Choice🫡🫡
conquer1.substack.com?utm_so…
Our product iteration improved 10X because of one change: debug app.
AI needs context about your existing product and what you are thinking next. So we gave every non-coder on the team GitHub access.
Not to ship code. To experiment.
They give AI full codebase context - design system, data, existing flows. Then ask it to build whatever idea they have in mind.
The real impact: they view the change directly inside the app.
Real device. Real data. Haptics. Animations. Audio. Things you cannot feel in Figma.
Ideas that took weeks to get from "thought" to "I can experience this on a device" now take hours. By non-devs.
We tried Lovable earlier for this. It got us partway. But without the actual codebase context, the design system never matched. Once Claude works on the real repo, the output fits the product instantly.
This is not about replacing Figma or developers. We still design properly, still build properly.
But the exploration phase shrank from weeks to hours.
Lakshay Nagpal retweeted
(7/10) At this moment, with multimodal AI, we are giving feedback that is inherently 'super personalised' to the student — making a real impact on their problem solving skills. & Homi is remebering the mistakes for future roadmap!
See these copies -- all these are actual school students in India using @HeyHomiApp in beta.
Lakshay Nagpal retweeted
(3/10) At Homi @HeyHomiApp, we have been trying to solve a peculiar Indian problem -- while keeping the same thesis of "not making kids dumb".
250+ million school students in India.
Every single day, we (students) write in our notebooks, it's an endless phenomenon!
Lakshay Nagpal retweeted
(2/10) Every edtech founder understands this, and is trying to chase how to replicate 1:1 learning with AI.
Education is the biggest orbit shifter, everywhere in the world, and AI gives us the opportunity to democratise impactful learning at scale!
And AI that thinks for the child is the worst thing we could build or rely!
Lakshay Nagpal retweeted
(1/10) The journey so far towards personalised learning has been worth noting.
From Khanmigo → ChatGPT Study & Learn → Claude's introduction of interactive equations → Koji
I saw the new product @brilliantorg and it's the most engaging, delightful, and well thought-out product — keeping the legacy of Brilliant alive.
This is a massive leap in 1:1 learning.
