Limin Ge
  • Founder
  • Products
  • Blogs
  • Contact
Limin Ge

Founder-led product studio building AI-native tools, games, and experiments you can try instantly.

© Copyright 2026 Limin Ge. All Rights Reserved.

Founder
  • Founder
  • Products
  • Blogs
  • Contact
Connect
  • LinkedIn
  • GitHub
  • X (Twitter)

Founder · Building AI-Native Organization

Hi, I'm Limin Ge. Founder & Engineer building products people use, play, and pay for.

I work in agentic systems, context engineering, AI-native workflow, and large-scale distributed systems.

Featured

Featured launches

A mix of live products, betas, and experiments.

Productivity

PostPlus

A platform that helps content creators quickly craft breakout-ready images and video assets.

See website•Web / iOS
Open PostPlus
Open Source

Shad Expo Studio

An open-source platform using regression testing and presentation/logic separation to control frontend style drift for AI-native teams.

Open source•GitHub
View GitHub
AI Companion

Stealth Mode

An emotional companion AI that chats, empathizes, and listens, helping users find virtual friendship and love.

Invite only•Web / iOS
Request access
Education

Ace-Assist

A general-purpose AI agent for students, helping them learn better in the AI era.

See website•Web
Open Ace-Assist

Featured

Featured articles

A starting list of essays and notes.

View all articles
Cover Image for AI-Native Engineering: 11 Hard Truths for 2025
Dec 4, 2025

AI-Native Engineering: 11 Hard Truths for 2025

A founder note on building AI-native organizations and systems.

Cover Image for Part One: The Pulse of a Small Town—Deconstructing the Survival Principles of America's Local Economies
Sep 9, 2025

Part One: The Pulse of a Small Town—Deconstructing the Survival Principles of America's Local Economies

This is the first article in our series, "From Rural Towns to the Future of Humanity: A Thought Experiment on an Economic Model." Please stay tuned for subsequent articles.

Founder notes

AI-Native Engineering: 11 Hard Truths for 2025

Principles I'm using to build AI-native organizations and products.

  1. 1.If a knowledge, methodology, or tech stack is older than 3 years, it is obsolete until proven otherwise.
  2. 2.Your codebase, docs, and meeting notes are not your backbone; your test case library is the only compounding asset.
  3. 3.AI is completely, fundamentally stateless.
  4. 4.We can accept AI mistakes as long as they do not kill the team before the next model upgrade.
  5. 5.Software complexity must flatten: from deep vertical stacks to wide horizontal systems.
  6. 6.The context window is the most critical computational resource every engineer must master.
  7. 7.Plan-Act, Test-Code, and Doc-Code-Doc are the new working loops of engineering.
  8. 8.The future of code is not abstraction but tiny, isolated, AI-readable units that stand on their own.
  9. 9.AI will never solve the first mile or the last mile; those remain stubbornly human.

Founder

I'm the founder behind every product in this studio.

Founder & Engineer focused on AI-native organizations and agentic systems.

Limin GeFounder & Engineer

Product Studio · Founder

Build apps that help people and entertain people.

Stealth Mode

An emotional companion AI that chats, empathizes, and listens, helping users find virtual friendship and love. Angel round valuation $15M.

Ace-Assist · Founder

AI agent for students connecting email, calendar, and files to build smart study workflows.

SpeakSharp.io · Founder

Top 10% of YC 24 Summer; CMU Nova Spark Grant; Swartz Center & Project Olympus member.

Cover Image for The Hidden Scaling Laws of Startup Engineering: What I Learned Building 50K Lines of Code in 2 Months
Sep 8, 2025

The Hidden Scaling Laws of Startup Engineering: What I Learned Building 50K Lines of Code in 2 Months

How doubling your codebase creates completely different engineering challenges - and why most teams aren't prepared for the transitions.

Cover Image for Farewell SaaS, Embrace the Agent: A 10,000-Word Deep Dive into the Rise of the "Results Economy" and the Future of Human Civilization
Sep 7, 2025

Farewell SaaS, Embrace the Agent: A 10,000-Word Deep Dive into the Rise of the "Results Economy" and the Future of Human Civilization

The origin of this article was a continuously deepening dialogue between myself and an AI. It began with a technical question about the future business models of software, yet l...

10.
AI-generated artifacts are not side effects; they are a new software modality and part of your engineering assets.
  • 11.The real power of AI IDEs and agents is not generation; it is ruthless, intelligent context selection.
  • Read the manifesto

    Founder notes

    Current state of LLM Risks and AI Guardrails

    Published in arXiv.org on June 16, 2024 · 66 citations on Semantic Scholar

    A survey of the main risks in deploying LLM systems and the guardrail patterns used to mitigate them, including bias and toxicity checks, prompt and agent safeguards, privacy concerns, and the tradeoffs required to ship these systems responsibly.

    Read the paper