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

# Knowledge Use Cases

> Canonical knowledge patterns that align AI with how your business operates.

<Info>
  These are canonical documents for the AI to refer to. They encode institutional
  knowledge so analysis reflects how your business actually operates.
</Info>

## Department Operating Guides (Sales, Marketing, Support, Finance)

* **Outcome**: The AI understands how each department works and frames analysis in the
  right operating context.
* **Include**: Org structure and responsibilities; core processes and handoffs;
  SLAs; cadences (pipeline reviews, forecast calls); definitions of success; common
  edge cases.
* **Link to**: Department/team nodes; key models; core metrics and dimensions;
  relevant entities (e.g., Opportunity, Ticket, Invoice).
* **Title examples**: `Sales Operations Guide`, `Marketing Analytics Operating Model`.

## Business Glossary and Taxonomy

* **Outcome**: Consistent terminology and fewer misunderstandings across teams.
* **Include**: Canonical terms; synonyms and forbidden terms; calculation notes;
  naming conventions; examples and counterexamples for tricky concepts.
* **Link to**: Models, metrics, and dimensions the terms govern.
* **Title examples**: `Enterprise Segment Glossary`, `Attribution Taxonomy`.

## Metric Interpretation and Decision Rubrics

* **Outcome**: Analyses read metrics the way your business does and recommend actions
  consistent with policy.
* **Include**: Metric purpose; leading/lagging relationships; how to read changes;
  expected ranges and seasonality; common pitfalls; decision criteria and next-best-
  actions.
* **Link to**: Metric nodes and the dimensions used to break them down.
* **Title examples**: `ARR Interpretation Guide`, `Activation Rate Decision Rubric`.

## Data Lineage, Quality, and Ownership

* **Outcome**: The AI respects data limitations and routes questions to the right
  sources.
* **Include**: Source systems; refresh cadences; known gaps/quirks; authoritative vs.
  derived datasets; owner contacts and escalation process.
* **Link to**: Models and pipelines; metrics that depend on them; data owner/team nodes.
* **Title examples**: `Revenue Model Lineage & Quality Notes`, `Attribution Data Owner Guide`.

## Strategic Initiatives and Quarterly Focus

* **Outcome**: Business Reviews and analyses prioritize current strategic goals.
* **Include**: Objectives and hypotheses; guardrails; success measures; relevant time
  windows; key stakeholders and dependencies.
* **Link to**: Project/initiative nodes; teams; impacted metrics; regions/categories.
* **Title examples**: `Q1 Growth Initiatives`, `Cost Optimization Program Overview`.

## Customer and Segment Definitions

* **Outcome**: Customer-facing analyses reflect real segmentation and account context.
* **Include**: Segmentation logic; named segment lists; strategic customers; lifecycle
  stages and triggers; notable exceptions.
* **Link to**: `Customer`/`Account` entities; segment dimensions; revenue/retention metrics.
* **Title examples**: `Enterprise Segmentation Framework`, `Strategic Accounts Playbook`.

## Pricing, Discounts, and Policy Constraints

* **Outcome**: Analyses interpret revenue and conversion with the right pricing context.
* **Include**: Discount policy; approval thresholds; common exceptions; how pricing
  impacts key metrics; reporting caveats.
* **Link to**: Revenue metrics (`ARR`, `Bookings`); deal/opportunity entities; Finance team.
* **Title examples**: `Discount Policy Guide`, `Pricing Context for Revenue Analysis`.

## Seasonality and Event Calendars

* **Outcome**: Variance is attributed correctly given seasonal effects and events.
* **Include**: Calendars (holidays, events, campaigns); expected uplift/drag; blackout
  periods; known interactions (e.g., weather, geo-specific patterns).
* **Link to**: `Region`, `Category`, and `Campaign` nodes; affected metrics and dimensions.
* **Title examples**: `Retail Holiday Context`, `Event & Seasonality Calendar`.

### Do vs Avoid

* **Do**: Make titles and descriptions explicit about scope and audience
* **Do**: Link to the exact nodes users query so the right guidance is referenced
* **Avoid**: Over-linking high-level nodes that pull unrelated context
* **Avoid**: Vague titles like "Marketing Guide" without scope or ownership