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

> ## Agent Instructions
> Start with /introduction/getting-started. Use the Inference API's Direct Query endpoint (POST /api/inference/query) with the newton-c-2.6 or newton-fusion-1.0 model (text, image, and video reasoning) or the omega-embedding encoder (time-series embeddings). ATAI_API_ENDPOINT is the base URL https://platform.u1.archetypeai.app with no version path; every endpoint path begins with /api. Pages whose descriptions are marked (Archived) document the legacy Lens runtime — do not use them for new projects.

# Contextualization Agent

> Temporally aligns sensor observations with dynamic context. Fuses context across heterogeneous real-time data sources, and generates time-stamped, context-aware descriptions.

> [!NOTE]
>
> This agent is currently in preview and is not available to all customers at this time.
> [Contact Sales](mailto:sales@archetypeai.team) for more information.

The agent combines sensor-based observations with contextual data to understand the conditions
under which detected events occurred.

It synchronizes dynamic context—such as weather, location, traffic, time, and operating
schedules—with physical behaviors and operational states to generate context-aware descriptions
for operators and downstream agents.

### Use Cases

* **Investigate incidents with surrounding operational context:** Fuses the detection with
  orthogonal, heterogeneous context streams, so hard braking on a dry road reads as driver
  behavior and the same event in heavy rain reads as weather.
* **Assess events across changing operating conditions:** Temporally aligns context that evolves
  over time with the event stream, so the same behavior is judged against the conditions it
  actually occurred under.
* **Enrich alerts with real-time situational information:** Adds situational detail to every
  alert without filtering, so no detection is ever removed.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.