Gists

Abstract

Integrating autonomous AI agents into enterprise architectures exposes critical security and latency vulnerabilities. The Autonomous Google API Agent (AGAA) solves this by enforcing a deterministic, zero-trust execution framework directly within Google Apps Script (GAS). By merging GASADK, dynamic REST endpoint resolution via GoogleApiApp, and the Developer Knowledge API through the Model Context Protocol (MCP), AGAA executes complex cross-domain workflows exclusively via natural language. It autonomously researches API schemas, mitigates server-side formula latencies, handles recursive pagination, and mathematically enforces local Role-Based Access Control (RBAC). AGAA enables true “Vibe Coding” across all Google APIs—including Workspace, Analytics, and YouTube—without bloated client libraries.

Overview

GASADK is a groundbreaking Agent Development Kit tailored specifically for the resource-constrained Google Apps Script environment. Driven by a deterministic Planner-Executor-Synthesizer (PES) architecture, it effectively bypasses traditional async Node.js assumptions to overcome the absolute 6-minute execution limit and synchronous blocking networking (UrlFetchApp). Featuring dynamic DAG planning, temporal context anchoring, and seamless integrations with MCP, A2A, and Google Drive-based Agent Skills, GASADK transforms GAS into a bulletproof, high-performance runtime for autonomous AI agents. Install via the dedicated library key to orchestrate robust, zero-latency multi-agent systems today.

Gists

Abstract

Google’s Agent Development Kit (ADK) revolutionizes autonomous AI agents, yet its standard Node.js-based asynchronous ReAct architecture is fundamentally incompatible with the restrictive, synchronous, and time-bound execution environment of Google Apps Script (GAS). To unlock enterprise-grade AI natively within Google Workspace, this paper introduces GASADK. By abandoning the cyclical ReAct loop in favor of a deterministic Planner-Executor-Synthesizer (PES) architecture, GASADK proactively manages execution constraints, synchronous network blocking, and payload limits. This framework successfully implements multi-agent orchestration, the Model Context Protocol (MCP), and Agent-to-Agent (A2A) communication directly within GAS, empowering developers to build highly resilient, serverless AI workflows that seamlessly manipulate Workspace applications.

GeminiWithFiles was updated to v2.0.16

• v2.0.16 (May 7, 2026)
  1. Introduced invoke_agent functionality to Agent Skills.
  2. Enabled subagent orchestration, allowing parent agents to spawn independent executing contexts (Subagents) for specialized tasks without polluting the main conversation history.

You can see the detail information here https://github.com/tanaikech/GeminiWithFiles

MoveFolder was updated to v1.0.3.

• v1.0.3 (May 06, 2026)
  1. Refactored the core script for better performance, safety, and readability.
  2. Enhanced error handling: The script now strictly verifies if file moves were successful before deleting any original source folders, preventing accidental data loss if permission errors occur.
  3. Introduced parallel processing using UrlFetchApp.fetchAll for much faster folder structure retrieval and folder creation.
  4. Added a standalone test script (test.js) to allow safe, automated validation of the library’s functionality.
  5. Updated the README documentation to make it more beginner-friendly and easier to follow.

You can see the detail information here https://github.com/tanaikech/MoveFolder

Gists

Implementing Progressive Disclosure in Google Apps Script

Motivation for Writing

As an active researcher and developer in the AI ecosystem, I have seamlessly integrated Agent Skills into daily workflows using tools like Claude Code, Gemini CLI, and Antigravity. However, I observed a pervasive tendency in the developer community—and initially within my own practice—to treat these capabilities as opaque black boxes. There is a distinct lack of granular understanding regarding the internal execution steps and the recursive orchestration occurring within Generative AI models when a skill mandates subagent delegation.

GeminiWithFiles was updated to v2.0.15

• v2.0.15 (May 6, 2026)
  1. Refactored the script entirely.
  2. Added support for Agent Skills (Progressive Disclosure architecture). You can now build autonomous agent workflows using skills stored in Google Drive.
  3. Added the skillFolderId property to the geminiWithFiles constructor to automatically discover skills, register necessary functions (activate_skill, read_skill_resource, run_dynamic_script), and manage the autonomous execution loop.
  4. Added run_dynamic_script tool to dynamically execute .js scripts stored within the skill folders.
  5. Enhanced generateContent to fully support multi-turn function calling loops.

You can see the detail information here https://github.com/tanaikech/GeminiWithFiles

Gists

Abstract

As Large Language Model (LLM) agents increasingly integrate numerous external systems, they suffer from Tool Space Interference (TSI), a phenomenon causing context bloat, attention dilution, and degraded reasoning accuracy. In this paper, we introduce the Agent-as-a-Tool paradigm—an evolutionary, practical implementation of the recently proposed Self-Optimizing Tool Caching Network (SOTCN) and Federated Context-Aware Routing Architecture (Federated CARA). By leveraging Retrieval-Augmented Generation (RAG) to dynamically discover and assemble stateful, autonomous sub-agents on the fly, this architecture completely eliminates TSI, enforces Zero-Trust execution boundaries, and achieves infinitely scalable AI orchestration.

Gists

A Comparative Study of Agentic Frameworks and Multi-Agent Orchestration

Abstract

The transition from passive chatbots to autonomous execution environments was cemented at Google Cloud Next ‘26 with the introduction of the Gemini Enterprise Agent Platform. This paper evaluates four cutting-edge AI agent methodologies for Google Workspace automation, developed by leading developers Martin Hawksey, Bruce Mcpherson, and Kanshi Tanaike. We deconstruct their structural approaches—CLI skill chaining, advanced emulation sandboxing, dynamic code generation, and A2A remote delegation—demonstrating how these community-driven innovations anticipated native Next ‘26 features like the official Agent Skills repository and Model Context Protocol (MCP) support. Building upon these foundations, we propose two novel frameworks: the Federated Context-Aware Routing Architecture (Federated CARA) for zero-trust, multi-cloud task routing, and the Self-Optimizing Tool Caching Network (SOTCN) to eliminate Tool Space Interference using dynamic semantic caching. This comparative synthesis maps existing and proposed models against Google’s new enterprise standards, offering a scalable roadmap for secure, highly dynamic multi-agent orchestration.

Gists

Abstract

Welcome to the Agentic Enterprise era. This article explores a paradigm shift in generative AI workflows by introducing an autonomous agent capable of dynamically creating, testing, and executing original tools. Utilizing Google Apps Script, Node.js emulation, and multi-agent orchestration, this architecture overcomes traditional limitations, enabling highly adaptable task execution.

Introduction

At Google Cloud Next 2026, a clear mandate was delivered: the era of generative AI as a passive assistant is over. We have entered the age of the Agentic Enterprise, where AI has transitioned from a software tool you deploy into an autonomous coworker you onboard. This identity shift is staggering. With models processing over 16 billion tokens per minute via direct API use, we are witnessing an industrial-scale migration toward autonomous workflows. In this new ecosystem, Workspace Intelligence eliminates tab-hopping, allowing users to seamlessly query across Google Drive, Gmail, and third-party platforms. Data has transformed from a reactive archive into a “System of Action,” driven by Deep Research Agents that bridge structured and unstructured data to prevent hallucinations.