If you're comparing structured GDF retrieval vs plain text for a client pilot, use the eval kit:

→

Guides AI — Testing & access Pilot evaluation checklist: register, create a portal, connect AI your way, save doc guides for reference, and report results. Plu Guides

- pilot checklist (register + portal + report template) and connector smoke tests.

→

Connecting AI to Guides Start here for a Guides pilot: register, create a portal, connect AI your way, optionally run a GDF benchmark, and report what wor Guides

- API keys, connect ChatGPT/Cursor, GDF vs plaintext benchmark (Section 3).

Bookmark both while reading (bookmark icon) - they stay on your Saved shelf in Reader.