> ## 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.

# Interpretation Agent

> Translates sensor behavior into natural-language explanations. Incorporates sensor metadata and domain knowledge, and provides grounded explanations with confidence.

> [!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 turns detected events and sensor behavior into clear, plain-language explanations.

It combines the detection with sensor metadata, state definitions, and domain knowledge to
explain signal behavior and make physical-world insights understandable and actionable across
operations teams.

### Use Cases

* **Explain detected anomalies in plain language:** Translates a label and a score, like "State
  3 at 14:02, confidence 0.87," into what the signal behavior means for the asset, written in
  the asset owner's own vocabulary.
* **Translate sensor behavior for operators and engineers:** Incorporates sensor metadata and
  domain knowledge into every explanation, so insights are understandable and actionable across
  operations teams without a specialized expert.
* **Summarize detected events for investigation:** Logs every event in a standardized entry
  (timestamp, asset, state, tag, and explanation), so triage starts from an answer instead of a
  raw detection.


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