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

# Context Manager

> The governed memory behind Quotable Agent, routines and articles: brand records you approve, the evidence they come from, never-claim rules, and team and personal context.

> [!NOTE]
>
> **Plans:** All plans · **In the app:** Settings → Context

The **Context Manager** is what Quotable knows about your brand, and how sure it is. Quotable Agent, Opportunities, routines and analyses all read from the same trusted memory, so a fact you correct here is corrected everywhere. Open **Settings**, then **Context** in the brand's settings.

```mermaid theme={"system"}
flowchart LR
  A[Evidence<br/>knowledge sources and pasted text] --> B[Governed memory<br/>brand records you approve]
  B --> C[Applied context<br/>Quotable Agent, articles, routines, analyses]
```

## Tabs

| Tab | What it holds |
| - | - |
| **Overview** | Context health, trusted and pending records, indexed evidence, active gaps, and what needs your attention |
| **Brand Records** | The facts about your brand: company, positioning, products, audience, tone, strategy |
| **Knowledge Base** | Evidence from connected sources and text you paste in |
| **Personal Context** | Your own preferences, plus rules shared with your team |
| **Skills** | Reusable instructions for Quotable Agent and routines. See [Skills](https://docs.usequotable.com/actions/skills.md) |
| **Intelligence** | Open questions, the fact graph, conflicts, and synthesis activity |

## Overview

The Overview shows four tiles: **Context health**, **Brand Records** (trusted and pending), **Evidence** (indexed documents and live sources) and **Active gaps**. Below them:

* **Needs attention**: up to four next steps, such as records drafted by AI that need review, missing categories, questions worth answering, records due for re-verification, failed documents, conflicts, or connecting a live knowledge source.
* **Trust and freshness**: structural coverage, human trust, freshness, evidence readiness and resolved decisions.
* **Recent evidence**: the last five documents indexed.

## Brand records

Brand records are the facts every agent uses. Each record has a type, a title (up to 120 characters), a description (up to 4,000), an optional expiry date, and up to 12 detail fields.

| Type | Records | Preset details | Used in |
| - | - | - | - |
| Company | One | Category, Market, Founded | Quotable Agent, articles, prompt suggestions |
| Positioning | One | Differentiators, Proof points, Against | Quotable Agent, articles, perception gap |
| Product | Many | Key features, Pricing, Main use case | Quotable Agent, articles, prompt suggestions |
| ICP | Many | Segment, Pain points, Jobs-to-be-done | Prompt suggestions, articles, coverage analysis |
| Persona | Many | Role, Goals, Objections | Articles, Quotable Agent, coverage analysis |
| Tone of voice | One | Style, Avoid | Articles, Quotable Agent |
| Strategy | Many | Priority, Target outcome, Time horizon | Quotable Agent, recommendations, articles, prioritization |
| Execution rules | Many | Cadence, Approval owner, Never do | Quotable Agent, articles, routines, recommendations |
| Custom | Many | None | Quotable Agent, articles |

### Create records

> [tab] Generate from website
>
> Reads your brand's homepage and drafts records from it. Sites that render their content only in the browser may return little.

> [tab] Import
>
> **Import brand material** takes pasted text or a single URL, up to 40,000 characters. Click **Extract cards** to draft records from it.

> [tab] Manually
>
> Click **Start manually** (or add a record) and fill it in yourself.

> [tab] From evidence
>
> **Synthesize evidence** drafts records from your Knowledge Base. It is enabled once at least one document is indexed, and also runs automatically after new evidence is indexed.

### Trust and review

Only **approved** and **locked** records that have not expired reach Quotable Agent and routines. Everything else waits.

| Badge | Meaning |
| - | - |
| AI draft / Needs review | Drafted by AI; waiting for a person |
| Locked | Approved and protected from automatic changes |
| Superseded | Replaced by a newer record; history kept |
| Rejected | Will not be used |
| Expired | Past its expiry date; no longer sent to Quotable Agent or routines, not deleted |

* Records you write by hand are saved as approved. Records drafted by AI start as pending.
* Approving, locking, rejecting, deleting or editing an AI-drafted record asks for a **Reason for your decision**. Editing one also asks which indexed document supports the change and whether that source is primary or secondary.
* The **Review queue** lets you approve, lock or reject in batches, with **Compare** to see the change against current memory.
* Each record has a **Version history** with **Restore**. Deleted records can be restored from **Recently deleted records**. **Roll back to a revision** undoes every later change as new revisions; nothing is erased.

### Review windows

Records go stale. Each type is due for re-verification after a set time since it was last verified:

| Type | Review after |
| - | - |
| Strategy | 45 days |
| Execution rules | 90 days |
| Positioning, Product | 120 days |
| ICP, Persona, Custom | 180 days |
| Company, Tone of voice | 365 days |

Records past their window show as due for review. Approved Strategy records also expire automatically when their window passes; locked records never do.

### Never-claim rules

A never-claim rule is a phrase or pattern your brand must never be credited with, such as "SOC 2 certified" before you are. Add rules in the **Never claim** panel of Brand Records.

| Field | Rule |
| - | - |
| Phrase or expression | 2–200 characters. Expressions use a restricted pattern syntax; unsafe ones show **Not enforced** |
| Reason | Required, 3–500 characters |
| Limit | 100 rules per brand. Each rule can be switched off or deleted |

While a rule is on:

* AI-drafted records that match it are dropped before they reach review.
* Approved records that match it are left out of what Quotable Agent, routines and analyses receive, and out of your llms.txt.

> [!NOTE]
>
> Never-claim rules filter the facts Quotable Agent and routines are given. They do not scan the text
> an agent produces.

### Other governance tools

* **Supersession**: replace one trusted record with another of the same type, with a reason. The old record keeps its history.
* **Factual corrections**: propose to update a record, mark it stale or reject it, backed by an indexed source. The record changes only after review.
* **Learning loop**: how often suggestions are accepted, and how answers performed by context pack. Feedback on Quotable Agent answers feeds it but never edits records directly.

### llms.txt

The **llms.txt** button copies or downloads a brand-facts file built only from approved or locked, unexpired records that no never-claim rule blocks. Publish it at the root of your site for AI crawlers.

## Knowledge Base

The Knowledge Base is the evidence behind your records: call transcripts, documents, CRM notes and support tickets.

> [!NOTE]
>
> The Knowledge Base, adding evidence and synthesizing records from evidence
> are on every plan.

### Add evidence

* **Connect a source.** Connectors for call recorders, document stores, CRMs and support desks are coming soon. See [Knowledge sources](https://docs.usequotable.com/integrations/knowledge-sources.md).
* **Paste text.** **Add evidence** takes a title (up to 200 characters), an optional source URL, and between 40 and 200,000 characters of text: notes, research, a transcript.

### Indexing

Every piece of evidence is indexed before agents can use it. Its status shows where it is:

| Document status | Meaning |
| - | - |
| pending, queued | Waiting to be indexed |
| indexed | Searchable and usable as evidence |
| failed | Could not be read; retry the source |
| skipped | Not indexed, for example held for review |
| stale | Older than a year; still searchable, no longer treated as current |
| superseded | Replaced by a newer version |

### Authority rules

Not every source deserves the same trust. **Authority rules** set how much a source, a kind of document, or a specific owner can establish on its own:

| Level | Effect |
| - | - |
| Primary | May establish a fact on its own |
| Corroborated | Needs a second source to be trusted |
| Secondary | Adds color only; never a source of truth |

Rules cap the model's judgment by default. Tick **Override the model's answer instead of capping it** to make a rule decide outright. The most specific rule wins: owner, then source, then document kind. Rules apply on the next synthesis.

### Retention

* Old versions of a document lose their text 90 days after being replaced; a placeholder remains so citations still resolve.
* Evidence older than 365 days is marked stale.
* Disconnecting a source removes its indexed copies and sends AI-drafted records based on them back to review.
* Deleting a document detaches it from records, and AI-drafted records that relied on it return to pending.

## Personal and team context

Brand records are facts. Personal and team context are preferences about how answers should look: which metrics you care about, how reports are formatted, what to prioritize.

| Layer | Who sees it | Who edits it |
| - | - | - |
| **Brand Records** | Everyone on the brand | Editors and above |
| **Team Context** | Everyone on the brand | Any editor adds or edits; only the author or a workspace owner removes |
| **Personal Context** | Only you, not even workspace owners | You |

Precedence runs from Brand Records, to Team Context, to Personal Context. The lower layers refine how answers are presented; they never override a fact.

Preferences have a category (Reporting, Priorities, Metrics, Communication, Workflow, Constraints, Custom), a title and a body. You can promote a personal preference to **Team Context**, propose either kind as a brand record, export to CSV, or delete them. The **Precedence and conflicts** panel shows what is in your current Quotable Agent context and what was left out, and why.

## Intelligence

* **Context gaps**: questions synthesis could not answer from evidence, ranked by how much the answer would matter. **Answer** (and store the answer as a brand record, team context or personal context), **Skip**, **Snooze** for a day, a week or 30 days, or **Assign** someone and send them the question.
* **Atomic fact graph**: each fact as a statement with subject, predicate and object, its authority, confidence, validity dates and evidence.
* **Conflicting evidence** and **Memory relations** (supports, contradicts, supersedes) that you confirm or reject.
* **Synthesis activity**: recent runs, with **Run again**, **Cancel** and **Stop after this batch**.
* **Fact history** with restore.
* **Perception gap** and **Prompt coverage** analyses, run on demand.

## Roles

Viewers can read the Context Manager. Everyone else with access to the brand can edit records, evidence, rules and gaps. See [Team and roles](https://docs.usequotable.com/workspace/team-and-roles.md).

## Next steps

> [card] [Knowledge sources](https://docs.usequotable.com/integrations/knowledge-sources.md)
>
> Connect call recorders, documents, CRMs and support desks.

> [card] [Skills](https://docs.usequotable.com/actions/skills.md)
>
> Write reusable instructions for Quotable Agent and routines.

> [card] [Quotable Agent](https://docs.usequotable.com/actions/quotable-agent.md)
>
> Ask questions grounded in this context.


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