A tool I built · Now live at zsper.com

The AI writing partner that keeps your voice yours.

Zsper remembers how you think and turns it into articles, newsletters, and LinkedIn posts that still sound like you. Here's the problem it solves — and why I built it.

3Formats, one brain
0Auto-publishes, ever
1Memory per voice
30dFree, no card

Why I built it

AI made writing fast. It also made everyone sound the same.

I write a lot. This blog is fifteen years of thinking about architecture, teams, and the decisions that don't have a clean answer. Writing is how I figure out what I actually believe — so when AI writing tools arrived, I leaned in hard.

They were fast. Uncomfortably fast. But something was off. Everything I generated started to sound like everything everyone else generated — the same cadence, the same “it's not just X, it's Y”tic, the same glossy, oddly American polish. The words were fine. They just weren't mine.

The problem isn't that the model can't write. It's that it doesn't know you. It forgets you the moment the tab closes, improvises your facts, and starts every draft from zero. For a founder, an operator, a creator — anyone whose voice is the entire point — a tool that quietly flattens that voice is worse than no tool at all.

So I built Zsper. Not a chat window with a longer memory — a pipeline. It keeps a persistent, inspectable memory of how you think, learned as a by-product of the writing you already do. Before it drafts a single line, it selects from that memory: your stances, your stories, the way you actually make an argument. Then it writes, and shows you the provenance of every choice.

It's the same philosophy as everything else on this site. AI writes the code; you still make the call. Zsper drafts. You stay the author. Nothing it learns and nothing it writes goes out in your name until you say so.

What makes it different

A memory, not a chat history.

It remembers how you think

A persistent, inspectable memory of your opinions, stories, and framing — corroborated over time, pruned when it stops being true. You never maintain a knowledge base; writing builds it.

One brain, three formats

Make the argument once, then publish it as an article, a newsletter, and a LinkedIn post — each native to its format, all in your voice, from the same memory.

You always make the call

No auto-publish. New stances and retired beliefs wait for your review. Every draft shows what it drew from, so nothing speaks for you behind your back.

Built India-first — for founders, operators, and creators here, with pricing and a voice that fit. See how it works at zsper.com →

Questions people ask

How is Zsper different from ChatGPT?

ChatGPT forgets you between sessions and improvises your facts. Zsper keeps a persistent, inspectable memory of your thinking, selects from it before it writes, and shows the provenance of every draft. The prompt is the least interesting part.

Do I have to maintain a knowledge base?

No — that's the point. Knowledge is a by-product of writing. You write and publish; the memory grows, corroborates itself, and prunes what stops being true. You only step in when it flags a conflict or a new stance for review.

Will it publish in my name without me seeing it?

Never. There is no auto-publish. Anything that speaks in your voice — a draft, a learned opinion, a retired belief — waits for your explicit approval.

Whose voice does it learn?

Yours — from the writing you import and the pieces you publish. Run more than one workspace and each keeps its own memory and voice, so a client's workspace learns the client, not you.

Now live

Write like yourself — at the speed of AI.

Zsper keeps the memory. You keep the voice. Try it free for 30 days, no credit card.

Made for Indian founders & creators · No auto-publish, ever