The Jet Admin Anthropic integration lets your app send prompts to Claude and read the response 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 document needs reading, or a record needs classifying, 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 Claude first: AI-assisted support consoles that draft a reply from a ticket thread, document and image Q&A screens that answer questions with a source attached, and data enrichment workflows that tag and summarize records as they arrive. Because Jet reads your own database alongside Claude, 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 Claude 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 Anthropic

1. In Anthropic, open console.anthropic.com and create an API key.
2. In Jet Admin, open your project and add a new resource, or pick Anthropic while creating a project.
3. Choose Anthropic and paste the API key.
4. Jet loads the Claude actions available: completions, tool use, and image or document analysis.
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.