ktx/docs-site/content/docs/getting-started/introduction.mdx
Andrey Avtomonov 4421fe1c12 feat(docs): visualize KTX ingestion with ReactFlow diagram
Reframe the introduction around the two user-facing ingestion outputs (wiki
and executable semantic layer) and replace the static product-mechanics card
flow with a ReactFlow diagram: sources fan into a sequential ingest pipeline,
which forks into wiki and semantic-layer outputs connected by a bidirectional
"references" edge. Drop the .ktx/raw-sources internal-implementation rows from
the intro table and update the content test to guard the new copy.
2026-05-18 16:18:01 +02:00

77 lines
2.7 KiB
Text

---
title: Introduction
description: What KTX is, how it works, and where to start.
---
import { ProductMechanics } from "@/components/product-mechanics";
<div className="not-prose mb-10">
<div>
<h1
className="max-w-full text-3xl font-extrabold tracking-tight break-words sm:text-4xl lg:text-5xl"
style={{
fontFamily: 'var(--font-display)',
background: 'linear-gradient(180deg, var(--color-fd-foreground) 0%, color-mix(in oklch, var(--color-fd-foreground) 75%, var(--color-fd-primary)) 100%)',
WebkitBackgroundClip: 'text',
backgroundClip: 'text',
color: 'transparent',
WebkitTextFillColor: 'transparent',
lineHeight: '1.1',
letterSpacing: '0',
}}
>
Make analytics context usable by agents
</h1>
<p className="mt-4 max-w-2xl text-lg text-fd-muted-foreground" style={{ lineHeight: '1.7' }}>
{'KTX turns warehouse metadata, semantic definitions, BI usage, and team knowledge into a wiki and executable semantic layer that database agents can trust.'}
</p>
</div>
</div>
## Why KTX
- Schemas show columns, not business rules.
- Agents need trusted metrics, joins, filters, caveats, and provenance.
- KTX captures that context before agents write SQL, docs, or semantic edits.
## What KTX creates
KTX ingestion turns source evidence into durable context files that agents can
search, review, and execute.
| Path | What it gives agents |
|------|----------------------|
| `semantic-layer/` | Executable measures, dimensions, joins, grain, filters, and segments |
| `wiki/` | Business definitions, caveats, policies, analyst notes |
<ProductMechanics />
## Use it for
- **Generate SQL** from approved measures, dimensions, joins, and filters
- **Explain provenance** with wiki context and warehouse evidence
- **Repair context** through reviewable YAML and Markdown diffs
- **Work alongside** dbt, LookML, MetricFlow, Looker, Metabase, and warehouses
Databases: SQLite, PostgreSQL, Snowflake, BigQuery, ClickHouse, MySQL, SQL
Server.
## Start here
<Cards>
<Card title="Quickstart" href="/docs/getting-started/quickstart">
Set up KTX and build your first context in under 10 minutes.
</Card>
<Card title="Guides" href="/docs/guides/building-context">
Hands-on workflows for scanning, ingesting, writing, and serving.
</Card>
<Card title="Writing Context" href="/docs/guides/writing-context">
Edit semantic-layer YAML and wiki Markdown safely.
</Card>
<Card title="CLI Reference" href="/docs/cli-reference/ktx-setup">
Complete flag and subcommand reference for every KTX command.
</Card>
<Card title="AI Resources" href="/docs/ai-resources">
Machine-readable docs and agent-facing setup notes.
</Card>
</Cards>