Conversational Analytics

Conversational Analytics: Chat With Your Database in Plain English

Dashboard-bound workflows trap your team: new questions require tickets, analysts get bottlenecked, refreshes lag. Conversational analytics is part of your AI SQL workforce: ask the question, get the chart, read the grounded narrative, and every verified conversation compiles into a reusable SKILL under the matching persona.

Chion is an AI SQL workforce. Conversational analytics is how you use it: ask in plain English, get a verified chart and a grounded explanation, then refine.

Watch the demo

Read-only SQL enforced Vault-encrypted credentials (AES-256-GCM) Your data stays yours

What is conversational analytics?

Query data by chatting in plain English. No SQL, no dashboards.

Conversational analytics is a way of querying data by chatting in plain English instead of writing SQL or building dashboards. You ask a question, the system generates and runs a verified SQL query, and returns a chart plus a written explanation. Each follow-up question keeps the context of the previous turn, so you can refine results by saying "break that down by quarter" or "exclude churned accounts."

How Chion's conversational analytics works

Three steps: connect, ask, get a verified chart.

Connect your database. Paste a read-only PostgreSQL connection string. Credentials are stored in an encrypted vault and never leave Chion's backend.
Ask a question. Type it the way you'd ask a colleague: "which customers churned last quarter and what did they spend?"
Get a verified chart. Chion returns an interactive D3 chart, the exact SQL it ran, and a written summary. Ask a follow-up to refine.

Every chart comes with an explanation

Grounded narratives built from actual query output, not generic summaries.

Most analytics tools hand you a chart and leave you to figure it out. We generate a structured narrative for every result: a grounded analysis built from the actual query output, not a generic summary.

Every narrative follows a mandatory arc: a headline that names all series with their direction and explicit date ranges, a key insight that identifies cross-series patterns like shared peaks or divergences, and per-series statistical facts: non-competing observations that each add new information.

Density-based narrative allocation

Simple charts get short answers. Complex data gets deeper analysis.

Not every chart needs the same level of narrative depth. A single-series bar chart with 5 rows doesn't need three paragraphs. We compute a data density tier deterministically in code (not by the LLM) and use it to gate which narrative fields get populated.

THIN

1 series, fewer than 10 rows

Summary only. Headline and key insight are set to null.

MODERATE

2–3 series

QA (question alignment) + summary. Key insight populated when cross-series patterns exist.

RICH

4+ series or high row count

All three fields: headline, key insight, and per-series facts. Full statistical analysis.

Multi-turn conversation context

Follow-up questions refine the prior query. No starting over.

Each conversation tracks entities and filters across turns. When you say "break that down by quarter," the system knows you're refining the prior analysis; it doesn't start from scratch. It uses keyword delta tracking to detect what changed between your current question and the previous one.

Filter changes are classified into four operations: add (new filter that didn't exist before), replace (same dimension, different value), subtract (remove a filter), and preserve (carry forward unchanged). The SQL gets rebuilt surgically: only the parts that changed get regenerated. Everything else carries over from the previous turn's verified query.

This is why follow-up questions are fast. We're not re-profiling your schema or re-resolving entities on every turn. We're applying a delta to a known-good query. See the 13-step verified SQL pipeline for the full architecture.

Looking for SQL generation only?

Chion also offers one-shot text-to-SQL generation to skip the conversational layer and paste verified SQL straight into your own tools.

Need a portable agent file? Chion exports your verified queries as a SQL Analytics Agent file (CHION.md) interchangeable with CLAUDE.md, AGENTS.md, and SKILL.md. Drop into Claude Code or Codex.

Chion vs traditional BI + AI copilots

Side-by-side against Tableau AI, Power BI Copilot, and Looker.

Feature	Chion (AI SQL workforce)	Tableau AI	Power BI Copilot	Looker
Pricing model: AI SQL workforce vs SQL copilot (per-team flat fee vs per-seat license)	Per-team flat fee, any seat count	Per-seat license	Per-seat license	Per-seat license
Skill library format (CHION.md / SKILL.md plain Markdown vs vendor language)	SQL skill library, plain Markdown, portable	No equivalent	No equivalent	LookML, vendor-specific, locked
Auto-generated SQL skills (CHION.md export for Claude Code / Cursor)
Connects directly to live PostgreSQL		Extract or live	Extract or live	LookML layer
No ETL / pipeline / modelling required
Ask ad-hoc questions in plain English				via Looker AI
SQL shown under every answer				LookML, not SQL
Two-layer SQL validator before execution
Per-team pricing (not per seat)
Time to first chart (new schema, no prior modeling)	Under 5 min	Hours to days	Hours to days	Days (LookML setup)
Grounded narrative with every chart		Explain Data	Smart Narratives
Starting price per team of 5	$29/mo	$135/mo+	$60/mo+	Quote-based

Competitor pricing at public rates (Tableau Creator + 4 Viewers, Power BI Pro x5). Looker pricing not publicly listed. The "Pricing model" and "Skill library format" rows reflect Chion's architectural differentiation: an AI SQL workforce is priced per team and ships a portable SQL skill library; AI copilots are priced per seat and ship vendor-locked modeling languages.

See our vault-encryption and read-only SQL security model → · Watch the 2-minute demo →

Frequently asked questions

8 answers about conversational analytics.

What is conversational analytics?+

Conversational analytics lets you query data by typing plain-English questions instead of writing SQL or navigating dashboards. The system generates verified SQL, runs it against your database, and returns an interactive chart with a written explanation.

How is conversational analytics different from traditional BI dashboards?+

Dashboards show pre-built views that someone else configured. Conversational analytics lets you ask any question on the fly: no ticket, no analyst, no wait. Each answer includes the SQL so you can verify it.

Do I need to know SQL to use Chion?+

No. You ask questions in plain English. Chion generates the SQL, verifies it against a contract, and runs it. The SQL is visible if you want to inspect it, but you never need to write it.

What databases does Chion support?+

Chion connects to PostgreSQL via a read-only connection string. Your credentials are stored in an AES-256-GCM encrypted vault and never leave Chion's backend.

Is my database data safe? Can Chion write to my tables?+

Chion enforces read-only SELECT queries with a hard row limit. It cannot INSERT, UPDATE, DELETE, or ALTER your data. Every query passes a read-only check before execution.

How does Chion verify the SQL is correct before running it?+

Each generated query passes through a multi-phase verification pipeline: schema alignment, contract enforcement, and a read-only safety check. Invalid queries are rejected before they reach your database.

Can I see the SQL Chion generated?+

Yes. Every chart includes the exact SQL that produced it. Click the query to view, copy, or run it independently in your own database client.

What happens when I ask a follow-up question?+

Chion tracks entities and filters across turns. When you say 'break that down by quarter,' it refines the prior query surgically: only the changed parts are regenerated. Everything else carries over from the verified previous turn.

Ask your data a question

Point it at your database and ask something. See what comes back.

Watch the demo