> ## Documentation Index
> Fetch the complete documentation index at: https://docs.writerzroom.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Adaptive Intelligence
> See and control the user-specific signals WriterzRoom carries into future generations.
**Adaptive Intelligence**, under Intelligence in the sidebar, is the control panel for the signals WriterzRoom carries from your own work into future generations.
Model weights are not retrained. Approved context is retrieved at generation time from what you've written, edited, and approved — the same way retrieval works for research sources.
## Learning Controls
Each source of personalization can be turned off independently:
| Control | What it feeds |
| ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------- |
| Learn from substantial edits | Passages you rewrote become future voice examples |
| Use prior work | Structure is grounded in retained work, avoiding repeat treatments |
| Use explicit feedback | Ratings, tags, and review outcomes shape recommendations |
| Use performance outcomes | Measured engagement is used as a format signal, where outcome data exists |
| Use verified claims | Approved, unexpired entries from the [Verified Claims](/product/verified-claims) registry are retrieved for relevant assignments |
Turning a control off stops that signal from being used in new generations; it does not delete history already recorded.
## Active Signals
The signals panel lists what evidence is currently available to the personalization layer — each with an evidence count and whether it's active or paused. A signal with zero evidence has nothing to draw on yet regardless of whether its control is on.
## Pinned Rules
Pinned rules are durable, freeform instructions applied to every generation for your account — for example, a standing correction like never describing the organization as an industry leader without evidence. Add or remove them at any time; a change applies to generations from that point forward.
## Learned Voice Examples
Voice exemplars are passages recovered from substantial human rewrites, not raw model output. A generation that was accepted unedited does not contribute a voice example; a paragraph you materially rewrote does. This is what "learn from substantial edits" actually populates.
Manage the approved facts adaptive intelligence can retrieve as evidence.
Style profiles define voice at the account level; adaptive intelligence refines it from your edits.