Analysts wait on the data team for queries they could describe in a sentence. This copilot reads your actual schema and turns the question into SQL that runs the first time.
sonnet4 daysPostgresOpenAIdbtMetabase
Claude
74ROI
88Scale
$2.4k92Saved
ROI for
README.md
Why this subagent
Analysts wait on the data team for queries they could describe in a sentence. This copilot reads your actual schema and turns the question into SQL that runs the first time.
It connects to your warehouse, writes the statement against real table and column names, then checks the EXPLAIN plan before handing anything back. You get a query you can paste straight into the editor, plus a plain note on what it returns and which tables it touches.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Translate the analyst's plain-English question into a single SQL statement, scoped to the tables it actually needs.
pending
Run EXPLAIN on the draft query and reject any plan that triggers a full table scan or a cartesian join.
pending
Return the final query plus a one-line summary of what it counts and which tables it reads.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given the schema and a natural-language question, return one validated SQL query and a one-sentence description of its result set.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.