The Jet Admin Google Gemini integration lets your app send prompts, images, video and documents to Gemini and read the results back into your own records, driven by the same tables, forms and record actions you already build in Jet. Whether a document needs reading, a record needs classifying, or your team needs to search by meaning rather than keyword, the whole workflow runs inside Jet, and every call is scoped by role and written to the audit log.

That covers what teams build on Gemini first: document and media processing screens that read a PDF, image or video attached to a record, natural-language search built on embeddings of your own data, and data enrichment workflows that tag and summarize records as they arrive. Because Jet reads your own database alongside Gemini, every prompt can pull in the exact record it's working on, and every response writes straight back to it.

Key benefits

• AI without a separate app. Generate text, summaries and classifications from inside the same screens your team already works in.
• Multimodal in one call. Send text, images, video or documents to a single model instead of stitching together separate tools.
• Prompts built from your own data. Pull fields from a record straight into a prompt, instead of copying and pasting between tools.
• Results written back automatically. Store a completion, summary or extracted field directly on the record it came from.
• Actions with a record. Every Gemini call runs inside your app, scoped by role, and written to the audit log.
• Complete workflows. Tie a generated result to everything that follows it: update a record, trigger a notification, route for review.

How to connect Jet Admin with Google Gemini

1. In Google AI Studio, create an API key for Gemini.
2. In Jet Admin, open your project and add a new resource, or pick Google Gemini while creating a project.
3. Choose Google Gemini and paste the API key.
4. Jet loads the Gemini actions available: completions, media analysis and embeddings.
5. Add the data sources you want to feed into prompts.
6. Generate the screens you need, then set role permissions on who can trigger AI actions.
7. Add actions and workflows on top: document processing on upload, natural-language search, and a review step before AI output is saved.