The LQ.AI Atlas LQ.AI's documentation, bound to the code it describes
234 documents

First hour with LQ.AI

The orientation path: what LQ.AI is and why, how to run it, how decisions are routed, the system shape, and how to tell what's real.

Step 4 — Run NDA Review against the sample document

The repository ships with a sample NDA at docs/quickstart/sample-nda.md (the same document linked from this walkthrough). It's a short, synthetic mutual NDA between Acme and Northbrook with several deliberate issues for the skill to surface — this is what the demo exercises against.

In the Project view:

  1. Click + New Chat. The chat opens with the Project's attachments (none yet) and context document already in the chat's context.
  2. Click + Files and upload sample-nda.md from the repository (or download it from docs/quickstart/sample-nda.md on GitHub).
  3. Click + Skills and select NDA Review.
  4. The skill exposes its inputs as form elements (this is the skill-input-form pattern from PRD §3.4 / DE-010). Fill in:
    • Perspective: recipient (Northbrook is receiving the NDA from Acme; we are the recipient party in this exchange).
    • Deal type: vendor procurement (Acme is a potential business partner; we're not in M&A diligence).
    • Other inputs: leave defaults.
  5. In the chat input, type something like: "Please review." (Or click the Run skill button — the skill is already attached, so you don't need a verbose prompt. This is a chance to also try Enhance Prompt; click the lightning-bolt icon next to the chat input and watch your "Please review." get rewritten into a structured legal prompt before submission.)
  6. Hit Send.

The skill runs. Streaming output appears in the chat over ~30–60 seconds depending on your model and connection.