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

# Knowledge settings

> Configure learning thresholds, embedding behavior, and the memory defaults inherited by agents.

Use **Knowledge → Settings** (`/knowledge/settings`) to inspect learning policy, the active embedding configuration, and inherited memory defaults. Each region loads and authorizes independently; one refused read does not mean every region is unavailable.

![Knowledge settings (light)](https://mintcdn.com/gloo-b243725a/xyq5perq6SLByPBn/forge/images/console/knowledge/settings-light.png?fit=max\&auto=format\&n=xyq5perq6SLByPBn\&q=85\&s=343537784ef778e0d54d6027cd0f4d80)

Knowledge settings — Forge Console at `/knowledge/settings`

## What you can do

* **Read the learning policy.** Every learning setting shows what it does, the value in force, its default, its allowed range and when it last changed.
* **Change a setting.** With `platform:manage`, edit a value within its rule and save it.
* **Check the embeddings model.** See the active provider, model and vector dimensions, and where to change them.
* **Read the memory defaults.** See the values an agent inherits when it sets none of its own.

## Change learning policy

1. Record the current value in force and the outcome you want to change.
2. Choose **Edit** for the relevant setting. Editing requires `platform:manage`.
3. Check the displayed rule and allowed range, enter the new value, then choose **Save**.
4. Confirm the persisted value in force. A rejected value does not become active.
5. Inspect resulting knowledge state and [Search quality](https://docs.gloo.com/forge/console/knowledge/search-quality.md) before making a second related change.

Settings can affect existing knowledge, not just future submissions. Changes to promotion thresholds, signal priority, rating bands, and failed-run handling re-derive outcome state. Preserve the reason for a policy change so later reviewers can explain it.

## Learning

The Learning area needs `knowledge:read`. It shows every knowledge learning setting with a one-line
plain summary of what it does, the value in force, its default, the range a new value must fall in,
whether a stored value overrides it, and when it last changed. A stored value that breaks its
setting's rule is classified by that setting's own resolver: "Partly applied" when the
resolver still keeps part of it, naming the dropped parts (a distillation list of company and team
keeps company, and team is ignored), or "Stored value ignored" when it keeps none. The value in
force is always shown. Without
`knowledge:read` it names
the permission it needs. The settings are platform-wide and grouped:

* **Ranking**: the ranking weight of each grade (proven, provisional, contested, ungraded). Search
  multiplies a case's score by its grade's weight; retired cases are always excluded.
* **Promotion**: the successes a case needs to become proven, per scope type; the signal priority
  when sources disagree about one run (the first source in the order that gave a signal wins; by
  default a workflow's domain outcome outranks an operator's rating, which outranks the Judge, and a
  failed run decides only when nothing else spoke, and moving system up changes that); the star rating bands; whether a failed run counts as a
  failure; the retrievals a long-term memory needs before it may become a provisional case (a run
  that recalled it must also have succeeded); and the chat message → long-term memory threshold,
  which moved here from
  [Platform › Chat](https://docs.gloo.com/forge/console/platform/settings). Company and global cases always also need a human
  to approve proven.
* **Curation**: how many recent evidence items each case keeps for display (1 to 200), and how
  many days an unused, unrewritten case waits before the weekly curator flags it stale for a
  steward (7 to 3650).
* **Distillation**: how many proven cases must share a pattern before a skill improvement is
  proposed (at least 3), the similarity at which two proven cases count as the same pattern (above
  0, at most 1), and the scope types whose cases may be distilled. Only company and global are
  offered or accepted: a skill is read across the workspace, so no narrower scope's
  cases are distilled. Choosing no scope turns distillation off.

With `platform:manage`, **Edit** opens an inline editor and **Save** stores the value. A value the setting's rule would ignore is refused before
it is sent, with the rule shown, and the server checks it again and refuses it as
`invalid_setting`. Without `platform:manage` each setting says so and cannot be edited. Changing the
proven thresholds, signal priority, rating bands or failed-run setting re-derives every case's
outcome state under the new value. Every change is written to the audit log as `platform_setting_set`, with
the value before and after, whether it was saved here or through the
[Knowledge API](https://docs.gloo.com/forge/reference/http-api/knowledge#settings-and-re-embed).

## Embeddings

* **Embeddings model** shows the active embeddings provider, model and vector dimensions, and
  whether embeddings are enabled. Viewing it requires
  `grants:read`, `policies:read` and `audit:read`; when the server refuses the read, the card names the permission it needs. The model is not editable here: change it on the
  [Embeddings capability page](https://docs.gloo.com/forge/console/platform/capabilities), which requires `platform:manage`.
  The providers are OpenAI (the default) and Gloo AI. Gloo AI authenticates with the access token
  the Gloo AI inference provider refreshes, so that inference provider must stay enabled with its
  credential. It embeds with `gloo-openai-text-embedding-3-small`. Switching providers clears a
  stored model the new provider does not serve and starts a re-embed.

The re-embed that follows a model change is started and followed on [Health](https://docs.gloo.com/forge/console/knowledge/health.md#re-embed).

## Memory defaults

The **Memory defaults** group (`/knowledge/settings#memory`) shows, read-only, the values agent
context assembly applies when an agent sets none of its own: session summary tokens, channel summary
tokens and the context budget fraction. They are fixed platform values, not settings, so this group
has nothing to edit. An agent overrides them on its Memory tab in Workforce. The
former Memory page is retired: `/knowledge/memory`, `/resources/memory` and `/workforce/memory`
(and any path under them) redirect here.

## Key state to watch

The settings report drift between what is stored and what is in force:

| State | Meaning |
| - | - |
| Stored override | A saved value replaces the default. Inspect the value in force before changing it. |
| **Partly applied** | The resolver accepts only part of the stored value and identifies the ignored parts. |
| **Stored value ignored** | The stored value fails the resolver's rule; the effective value is shown separately. |
| Region names a missing permission | Resolve access for that region. Other regions may still be usable. |
| Model changed but search is incomplete | Follow the re-embed run in [Health](https://docs.gloo.com/forge/console/knowledge/health.md). |

Source change review is configured in each source's drawer, not as a global Learning setting. See [Sources](https://docs.gloo.com/forge/console/knowledge/sources.md#review-source-changes).

## Related surfaces

* [Search quality](https://docs.gloo.com/forge/console/knowledge/search-quality.md): check retrieval after a policy change.
* [Health](https://docs.gloo.com/forge/console/knowledge/health.md): follow a re-embed after a model change.
* [Sources](https://docs.gloo.com/forge/console/knowledge/sources.md): per-source change review.
* [Capabilities](https://docs.gloo.com/forge/console/platform/capabilities): change the embeddings model.


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