Walkthrough · conversational insights

Question → chart → follow-up → drill.

One conversation, four scenes. Watch the chart-selector pick the right visual at every level (line → bars → table), follow-ups ship pre-validated SQL so the runtime skips nl-to-sql, and the conversation crosses Engines into Advisory without losing context.

Walkthrough · 1 of 4
Step 1 — Type a revenue question into the Reactor. The LLM router resolves the system (Salesforce + Snowflake), the nl-to-sql atom builds the query, sql-executor runs it, chart-selector picks a line chart, and the narrative streams in.
quadrazene.app/reactor
quadrazene v0.2.1
Quadrazene
ReactorComposeRecipesInboxGovernanceRecords
⌘K
User
Why did revenue drop in March?
Insightsvia salesforce + snowflake · 3.4smsg_revenue_q1
Jan$8.42MFeb$9.18MMar$7.50MApr$9.62M

March revenue fell -18.3% MoM (Feb → Mar). The dip is concentrated in Enterprise; SMB and Mid-market are roughly flat. April recovered, suggesting a one-month event rather than a structural change.

▸ Inspect SQL
SELECT date_trunc('month', closed_at) AS month, SUM(amount) AS revenue
FROM salesforce.opportunity
WHERE stage = 'Closed Won'
  AND closed_at >= date_trunc('year', now())
GROUP BY 1 ORDER BY 1;
nl-to-sql · 412mssql-executor · 280mschart-selector · linefollowup-generator · 4
Suggested follow-ups(each ships pre-validated SQL — clicking skips nl-to-sql)
Break March down by segment
Compare March to plan
Show YoY for the same months last year
Top 5 customers driving the drop
Live walkthrough — click a button or use the rail to navigate.

Try this with your own warehouse.

Request a demo