In the development of autonomous agents using Large Language Models (LLMs), restrictions such as context window limits and session fragmentation pose significant barriers to the long-term accumulation of knowledge. This study proposes a "self-evolving framework" where an agent continuously records and refines its operational guidelines and technical knowledge—referred to as its SKILL—directly onto a local filesystem in a universally readable format (Markdown). By conducting experiments across two distinct environments featuring opaque constraints and complex legacy server rules using Google's Antigravity and Gemini CLI, we demonstrate the efficacy of this framework. Our findings reveal that the agent effectively evolves its SKILL through iterative cycles of trial and error, ultimately saturating its learning. Furthermore, by tr
Kanshi TANAIKE tanaikech
This is an appendix for https://gist.github.com/tanaikech/da47643a4b59578092f0129a9eb0c9c5, Medium, and DEV.
A.1. Directory Structure
Directory Structure for Antigravity:
This article demonstrates how to build an adaptive learning agent using Agent-to-User Interface (A2UI), Gemini, and Google Apps Script. We explore a system that generates personalized quizzes, tracks performance in Google Sheets, and dynamically adjusts difficulty to maximize learning efficiency within the Google Workspace ecosystem.
This article explores A2UI (Agent-to-User Interface) using Google Apps Script and Gemini. By generating dynamic HTML via structured JSON, Gemini transforms Workspace into an "Agent Hub." This recursive UI loop enables complex workflows where the AI builds the specific functional tools required to execute tasks directly.
This article details the development of Smart Stowage Optimizer, a web-based digital twin for logistics that bridges the gap between physical safety and artificial intelligence. By integrating Gemini 3 Pro, the system solves the 3D Bin Packing Problem (3DBPP) using advanced spatial reasoning. Built with React 19 and Three.js, the application visualizes physics-aware load stability in real-time, offering a comparative analysis between traditional heuristic algorithms and modern generative AI agents.
This article explores implementing the Agent-to-User Interface (A2UI) protocol within Google Apps Script. It demonstrates utilizing Gemini's structured output to render secure, dynamic, server-driven UIs—like booking forms and event lists—directly inside Google Sheets, streamlining workflows without complex external infrastructure.
The Gemini API now supports external file URLs, allowing developers to process data directly without uploading it first. This article demonstrates how to leverage this update to integrate Google Workspace resources—including Google Sheets, Docs, Slides, and Apps Script—into Gemini’s workflow, covering both public and secure private access methods.
This article demonstrates how to implement Google's A2UI (Agent-to-User Interface) using Google Apps Script (GAS). By porting official Python/TypeScript examples to GAS, we show how to create dynamic, AI-generated interfaces within Google Workspace, enabling flexible business automation and interactive user experiences without complex server infrastructure.
Published: January 3, 2026
Author: Kanshi Tanaike
Analyzing StackOverflow data (2008–2026) reveals a massive activity decline post-ChatGPT. Using Google Apps Script as a case study, this report quantifies the migration from human support to AI. We explore how the platform is pivoting from a help desk to a critical verification layer for AI-generated code to prevent model collapse.
This article introduces a Google Apps Script-based Agent2Agent architecture to solve Tool Space Interference. While the provided demonstration utilizes a single server for testing purposes, the architecture is designed for distributed task execution. By running multiple category-specific A2A servers in parallel, users can achieve scalable, high-efficiency agent networks.
NewerOlder