‘Coding is becoming plain English’: Nithin Kamath builds personal AI agent to tackle spam
Earlier, Kamath highlighted a massive shift in the tech landscape: Large Language Models (LLMs) have evolved from “hallucinating" random text in 2023 to gaining the approval of Linus Torvalds in 2026.
- Feb 20, 2026,
- Updated Feb 20, 2026 5:22 PM IST
In a glimpse of how artificial intelligence is quietly reshaping everyday workflows, Nithin Kamath, CEO of Zerodha, shared how he built a personal AI-powered tool to tackle one of his biggest daily frustrations—spam emails — underscoring how rapidly accessible AI solutions are moving from experimentation to real-world utility.
In a post on X (formally Twitter), Kamath wrote, “Dang! I have my first AI agent running. I built a small workflow for myself to identify spam emails using Google Studio. The best part about the tool is that you can define the rules. For example, this is one of the rules (image): Spam emails are my biggest personal problem. I was wasting at least 30 minutes a day marking emails as spam, even with different filters. And I’m addicted to seeing my inbox empty. So, to everyone who has been sending me unwanted emails: please spam my inbox now.”
Earlier, Kamath highlighted a massive shift in the tech landscape: Large Language Models (LLMs) have evolved from “hallucinating" random text in 2023 to gaining the approval of Linus Torvalds in 2026.
Writing on X, Kamath noted that Torvalds, the creator of Linux and historically a skeptic of overhyped tech, now admits LLMs can generate code superior to his own. “It’s remarkable how good these models have become… to the point where they’re on par with, or better than, humans across numerous domains," Kamath stated.
Kamath’s most striking observation involved the democratization of tech. He cited the example of an individual named Karthik, who built a functional website with a quiz despite having “zero programming knowledge."
“This is a guy who used to play words like ‘Dog’ and ‘Fan’ in Scrabble," Kamath joked, adding that the ease with which non-techies are now building sophisticated tools has given him “full FOMO."
As LLMs move from “vibe coding" toy projects to production-grade software, the industry is bracing for new frameworks. The old adage that “programming is 90% thinking and 10% typing" has finally become a reality, potentially making the “language" of the future not Python or Rust, but plain English.
In a glimpse of how artificial intelligence is quietly reshaping everyday workflows, Nithin Kamath, CEO of Zerodha, shared how he built a personal AI-powered tool to tackle one of his biggest daily frustrations—spam emails — underscoring how rapidly accessible AI solutions are moving from experimentation to real-world utility.
In a post on X (formally Twitter), Kamath wrote, “Dang! I have my first AI agent running. I built a small workflow for myself to identify spam emails using Google Studio. The best part about the tool is that you can define the rules. For example, this is one of the rules (image): Spam emails are my biggest personal problem. I was wasting at least 30 minutes a day marking emails as spam, even with different filters. And I’m addicted to seeing my inbox empty. So, to everyone who has been sending me unwanted emails: please spam my inbox now.”
Earlier, Kamath highlighted a massive shift in the tech landscape: Large Language Models (LLMs) have evolved from “hallucinating" random text in 2023 to gaining the approval of Linus Torvalds in 2026.
Writing on X, Kamath noted that Torvalds, the creator of Linux and historically a skeptic of overhyped tech, now admits LLMs can generate code superior to his own. “It’s remarkable how good these models have become… to the point where they’re on par with, or better than, humans across numerous domains," Kamath stated.
Kamath’s most striking observation involved the democratization of tech. He cited the example of an individual named Karthik, who built a functional website with a quiz despite having “zero programming knowledge."
“This is a guy who used to play words like ‘Dog’ and ‘Fan’ in Scrabble," Kamath joked, adding that the ease with which non-techies are now building sophisticated tools has given him “full FOMO."
As LLMs move from “vibe coding" toy projects to production-grade software, the industry is bracing for new frameworks. The old adage that “programming is 90% thinking and 10% typing" has finally become a reality, potentially making the “language" of the future not Python or Rust, but plain English.