Google Cloud

AI Applications on Google Cloud

I build agents on Gemini Enterprise that read company documents and act through APIs.

What I Do

Build an agent on Gemini Enterprise, then deploy it on Google Cloud

Ground the agent: I load your published documents into Gemini Enterprise. The agent answers from those files. Each answer cites the page. If the files do not contain the answer, the agent says so.
Connect your systems: The agent calls APIs on your system of record. It reads a file, checks published rules, and writes the result. A person remains the human gate.
Deploy on Google Cloud: I deploy the agent on Gemini Enterprise Agent Platform. Source code is stored in your repository. The application runs in your Google Cloud environment.

Case Studies

Public GitHub repositories for this work

Certificate of Analysis intake into Acumatica

Demo in progress

A Gemini Enterprise agent that reads a Certificate of Analysis PDF, checks the values against the inspection plan in Acumatica, and writes hold or release on the lot. This repository is a demo in progress, not a live warehouse system.

Receiving dock

Gemini Enterprise

Acumatica ERP

Certificate of Analysis PDF

read inspection plan

tests and limits

extract values and check rules

write inspection results

hold or release the lot

Receiving dock → Gemini Enterprise → Acumatica lot hold or release.

github.com/kborovik/acu-google-qms