Your reviewed SQL should survive the next tool change
This 28-second video is about what survives a tool change. A query your team reviewed and saved compiles into a skill for Claude Code or Codex, and each of those runtimes keeps its own wrapper, its own database connection, and its own behavior.
Chion turns the queries teams already trust into SQL skills your team keeps under version control rather than dashboard widgets locked inside the BI tool.
Problem. Switching off a BI dashboard usually means rewriting every chart and query in the new tool. What Chion does. Teams keep the SQL they already reviewed as compiled skills, then connect each runtime they use to the database themselves.
Published ·28sShort
Want a walkthrough on your own schema?
28-second demo: what survives a tool change. A saved SELECT compiles into a skill for Claude Code or Codex, each with its own connection.
What this short shows
A short framing of the migration story: queries a reviewer saved are compiled into skills, those skills are Markdown files your team keeps under version control, and the analytics team owns the query logic instead of leaving it inside a dashboard tool.
No rewriting from scratch
Your existing SQL (dashboard queries, scheduled reports, ad-hoc analyses) is the starting material. Chion compiles each query with business context, then makes it retrievable. There is no green-field rewrite, no parallel system to maintain.
One reviewed SELECT, several runtimes
The saved SELECT is the shared part. Chion Studio, Claude Code, and Codex each read it from the same compiled skill, but each one supplies its own database connection and its own wrapper, so results depend on the role you granted in that runtime rather than on a guarantee of identical behavior.
Read transcript
Recorded May 15, 2026. The page copy above carries the current product vocabulary.
00:00This is why analytics teams are switching to Chion.
00:03It begins with the queries you already trust: the ones powering your existing dashboards, the ones buried inside team folders, the ones your analysts have validated over years of operational use. Bring them into Chion.
00:09Chion converts those queries into retrievable Skills and reusable SQL scripts, each annotated with the business context that makes them safe to share across teams.
00:16Use the resulting library inside Chion Studio to converse with your data directly. Or take the same Skills to Claude, GPT, or Gemini and converse there.
00:23Same answers. Same business logic. Wherever your team prefers to work. Your analytics intelligence is no longer locked inside a single tool.
Frequently asked questions
Common questions about Chion demos and the underlying product.
How is Chion different from other text-to-SQL tools?
Chion enforces three invariants most SQL chatbots skip: every query is read-only SELECT (no writes), every query passes a two-layer validator before execution, and credentials are stored in an AES-256-GCM encrypted vault, never cached in application memory.
Can I use Chion Skills inside Claude Code or Codex?
Yes. The compiled bundle is plain Markdown, and you keep the artifact. Each of those runtimes reads it from its own path and needs its own database connection, so the file travels while discovery and execution stay runtime-specific.
What databases are supported today?
PostgreSQL is the production target. The demos use PostgreSQL 14 fixture databases. MySQL, BigQuery, and Snowflake are on the roadmap.
Does Chion ever write to my database?
No. All generated SQL is SELECT-only with LIMIT enforcement at the validator layer. INSERT, UPDATE, DELETE, and DDL are blocked in code, not by LLM instruction.
Can I run a demo on my own schema?
Yes. Connect your PostgreSQL database with read-only credentials and start asking questions. The trial is 7 days.