Panel permissions, unchanged
Tools check the panel's own module, branch and report permissions, so an admin can only ask about what they could already open.
AI support assistant — reads only what you're allowed to see
Cortex lives inside the company's admin panel. Admins ask questions in plain English and get answers from live business data in seconds — through read-only tools that respect the panel's own permissions and mask personal data before anything reaches the model.
two systems, one signed bridge
The AI service never touches the database directly — it can only call tools the panel exposes, over a narrow, signed channel.
guardrails, not bypasses
Every answer goes through the same rules the admin panel already enforces — Cortex adds guardrails, it doesn't bypass any.
Tools check the panel's own module, branch and report permissions, so an admin can only ask about what they could already open.
Phone numbers, emails and salary data are masked before anything reaches the AI model.
Services talk only through HMAC-signed requests over a private Unix socket, protected against replayed requests; chats expire automatically.
tested like any production system
An assistant that reads business data has to be tested and watched like any other production service.
Built from real admin questions. On its latest full run it passed in full with zero privacy or access leaks.
A Next.js dashboard tracks usage, answer rate, response time, AI cost against budget, conversation review and the health of each tool.
In-chat thumbs-up / thumbs-down ratings feed back into review, so weak answers surface quickly.
router → tools → permissions → masking → answer
Pick a sample question to replay the steps Cortex goes through before it answers.
admin> choose a sample question
Illustrative only. The real system's tools, prompts and data are private.