The Jet Admin OpenAI integration lets your app send prompts, generate completions, summaries and images, 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 ticket needs summarizing, a lead needs classifying, or a document needs its fields extracted, 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 OpenAI first: AI-assisted support consoles that draft replies from a ticket thread, data enrichment workflows that tag and classify records as they arrive, and document processing flows that extract structured fields from an upload. Because Jet reads your own database alongside OpenAI, 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.
• 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 OpenAI 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.
• Human review where it matters. Draft with AI, then have a person approve before anything sends or publishes.

How to connect Jet Admin with OpenAI

1. In OpenAI, open platform.openai.com/api-keys and create a Secret key.
2. In Jet Admin, open your project and add a new resource, or pick OpenAI while creating a project.
3. Choose OpenAI and paste the Secret key.
4. Jet loads the OpenAI actions available: completions, embeddings, moderation and image generation.
5. Add the data sources you want to feed into prompts, for example the record fields you want summarized or classified.
6. Generate the screens you need, then set role permissions on who can trigger AI actions.
7. Add actions and workflows on top: auto-tagging on record creation, ticket summaries, and a review step before AI output is saved.