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

# Causal graph overview

> A visual map of cause and effect in your domain — used to explain, verify, and analyze.

A **causal graph** is a diagram of the variables in your domain and the causal edges between them. It looks like a network — nodes are things you can measure (rates, temperatures, prices), edges are the causal links between them.

You use it for three things:

1. **Explain agent reasoning** — "the Agent recommended X because A causes B causes X."
2. **Verify agent answers** — flag outputs that contradict the graph.
3. **Analyze interventions** — "if we changed X, what would happen to Y?"

## When to build a causal graph

* Your Agent answers questions where **being wrong has consequences** — finance, medical, engineering.
* Your domain has **well-understood cause-and-effect** you can capture.
* You want Agents to **cite mechanisms**, not just correlations.

If your domain is fuzzy or the domain expertise is tacit, start with knowledge and memory. Add a causal graph only when you're sure of the structure.

## Graph shape

* **Nodes are variables**: continuous (blood pressure), discrete (department), or binary (fraud yes/no).
* **Edges are causal**: an arrow from A to B means "changes in A cause changes in B".
* **The graph is a DAG** (directed acyclic). Cycles are rejected — they don't make causal sense.

## Building a graph

Two main paths:

<CardGroup cols={2}>
  <Card title="Manual authoring" icon="pen" href="/build/causal-graph/variables">
    Add variables and edges by hand. Best when you're the domain expert.
  </Card>

  <Card title="Extract from documents" icon="wand-magic-sparkles" href="/build/causal-graph/extraction">
    Let Nora propose variables and edges from your knowledge. Review, edit, accept.
  </Card>
</CardGroup>

Most workspaces mix: seed with extraction, refine by hand.

## Using a graph

<CardGroup cols={2}>
  <Card title="Verify agent answers" icon="shield-check" href="/build/causal-graph/verification">
    Cross-check every answer against the graph before it goes out.
  </Card>

  <Card title="Analysis sessions" icon="microscope" href="/build/causal-graph/analysis">
    Interactive exploration — hypothesize, test, iterate.
  </Card>

  <Card title="Attach to an agent" icon="link" href="/build/causal-graph/attach">
    Give an Agent the graph as a first-class knowledge source.
  </Card>
</CardGroup>

## Draft & publish

Graphs are versioned. You can edit in Draft (staged changes shown as pending), and publish when ready. Only published graphs are used in verification. Rollback is instant.

## What causal graphs are not

* Not a replacement for knowledge. Keep your docs.
* Not a symbolic AI system. Your Agent still uses an LLM; the graph is a check, not the reasoner.
* Not a general knowledge graph. It's specifically for causal relationships. If you want general entity relationships, use memory graphs.