Data Analyst
Data analysis and querying
Answers questions from your warehouse or your spreadsheets. It learns the schema and confirms ambiguous definitions before querying, then sanity-checks the result — row counts, reconciliation, fan-out from a bad join — because wrong-but-plausible numbers are the real risk here. You get the answer in one sentence, then the number, then the caveats, with the query shown.
Connects with
Connect these once. Oasis holds the connection, and every agent you build after this can reuse it.
BigQueryRequired
SnowflakeRequired
MetabaseRequired
Google SheetsRequired
- +Custom toolConnect any other tool from thousands of available integrations.
Skills it ships with
How it runs
- Foundation
OpenAI Agents
- Model
- GPT-5.6 Terra
- Reasoning
- High effort
- Per run
- Up to 40 turns
- Memory
- Learns across runs
- Browsing
- Off
- Category
- Research
- Data
- Sql
- Analysis
Frequently asked questions
Can Data Analyst query both a warehouse and spreadsheets?
Yes. It answers questions from warehouse data or spreadsheets and learns the schema before querying.
How does it catch wrong-but-plausible numbers?
It sanity-checks row counts, reconciliation, and fan-out from bad joins. It also confirms ambiguous definitions before running a query.
What does an analysis answer include?
You get the answer in one sentence, the number, the caveats, and the query used.
Which data systems are listed for this workflow?
The catalog lists BigQuery, Snowflake, Metabase, and Google Sheets. Define the metric and segment you want compared.
Agents like this one
Put Data Analyst to work today
Add it to your Oasis, review its setup, and hand it the first task.