Delegated Power: Showcasing a Google Workspace Admin Toolbox Concept in AppSheet and Apps Script

The Google Admin Console is a powerful engine, but it often becomes a bottleneck for delegated tasks. IT teams frequently find themselves trapped in “Admin Debt,” repeating manual steps because granting full administrative access to others is a security risk.

At the Google for Education IT Admin Summit in London, I shared a session on how to move from a static interface to a dynamic, automated engine. The goal is to build an “Admin Toolbox” that showcases how some Admin SDK and other Workspace API capabilities can be integrated into secure, self-service applications using AppSheet and Google Apps Script.

For those who couldn’t attend, or for those who want to dig into the code, I’ve made the session guide available below.

“We are building a data bridge that turns raw directory records into a functional database that understands who people are and, more importantly, who they report to.” — Session Guide: The Automated IT Toolbox

Practical Builds in the Toolbox

The session guide covers four distinct areas where these technologies intersect to solve common IT headaches:

1. Hierarchical Directory Apps: Building a connection to the Admin SDK to create a searchable directory with security filters based on reporting lines.
2. Automated Shared Drive Provisioning: A workflow where AppSheet handles the request and Apps Script acts as the administrator to create and name drives automatically upon approval.
3. ChromeOS Management: Using the Reports API to create a live activity feed of login events and issuing remote commands like “Lock Device.”
4. AI-Powered Damage Reports: Utilising the Gemini API to analyse photos of damaged hardware. Users can snap a photo, and the AI provides a structured analysis of the severity and required parts.

Gemini as a Development Partner

A key takeaway from the session was that I didn’t write any of this code from scratch. Instead, I used the Gemini App as a pair programmer. While Gemini was excellent for standard data tasks, it reached its limits when handling more obscure or less documented API calls. In these areas, my existing knowledge of the Workspace platform was essential. I had to refine my prompts and provide specific technical context to guide the model toward a reliable solution. It highlights that while AI is a powerful assistant, it still needs a knowledgeable pilot to navigate the complexities of advanced APIs.

The full session guide includes code snippets as well as some of the advanced ‘watch’ and Gemini API structured output.

Source: Google Doc | GitHub Repo