> ## Documentation Index
> Fetch the complete documentation index at: https://quintsecurity.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Intent Model (Preview)

> The on-device intent model that judges whether an agent's stated intent licenses its actions. In development.

# Intent Model (Preview)

<Note>
  In development. This entry describes direction and engineering progress, not a shipped, generally available feature. No detection-accuracy claims are made here.
</Note>

Quint's behavioral approach reads what an AI agent *says* it is doing and checks whether that intent licenses what it actually does. The Intent Model is the on-device component that scores that relationship: given a stated intent and a concrete action, does the intent license the action, or does the action exceed it.

## What this is building toward

* **On-device, privacy-first.** The model runs at the endpoint. Conversation content stays on the endpoint. Only structured, de-identified geometry is ever used for learning, never raw text.
* **The model proposes, the scope disposes.** The Intent Model never makes an enforcement decision on its own. Its judgment shapes a scope that is then enforced deterministically, alongside fixed sensitivity floors, policy ceilings, and a kernel truth channel the agent cannot author. Fooling the model still leaves an attacker inside those deterministic limits.
* **Calibrated per policy key.** Operating thresholds are calibrated per action class and sensitivity, not by a single global setting, so the decision boundary reflects the real risk of each capability.

## Engineering progress

* Established a **leak-free evaluation methodology** for intent-to-action licensing. The instrument is constructed so that a model cannot appear accurate by reading the action shape alone; it must judge the actual relationship between intent and action. Rigorous, gameable-metric-resistant evaluation is a foundation we are building before making capability claims.
* Confirmed an **on-device, no-GPU training path** for the everyday model update, keeping the learning loop cheap and the endpoint footprint bounded.
* Upgraded the on-device encoder to a **larger, more capable model**, chosen and evaluated on the same leak-free instrument. It continues to run at the endpoint, per turn and asynchronously (off the blocking path), and the everyday model update remains a cheap, GPU-free retrain. No conversation text leaves the endpoint.

## Status

Pre-general-availability. We will describe measured capabilities here once they are validated on the leak-free evaluation at scale. See the platform roadmap (Adaptive) for how the Intent Model fits the broader release plan.