Query company data through a conversational agent
Block uses Claude through Databricks in its open-source goose agent to generate SQL, query datasets and connect internal tools. The company reports adoption across 15 job profiles. Reported engineering time savings concern goose's broader use and do not isolate natural-language data access.
Source checked: the source link is valid and the automated fact check passed. The summary is AI-assisted. This is not human verification. Check the original source before relying on its claims.
For whom
Business analysts and operations staff at large firms; data literacy and centrally managed integrations.
Not for
Not suitable for unrestricted database access without existing permission controls.
Brain Score
- Impact
- 1/2
- Evidence
- 2/2
- Reproducibility
- 0/2
- Maturity
- 2/2
- Reach
- 2/2
Five values from 0 to 2. The total has a minimum of 1. A reading aid based on the source, not an independently measured performance result. How the score works
Still current?
Partly, better ways exist
Today: Run goose with a supported Claude model on Databricks; Claude 3.7 Sonnet has been retired there.
Augments or replaces?
Augments your skills
Today: Employees define the question, interpret returned data and decide what to do; the agent handles SQL and tool access.
Original source
- Type
- Vendor
- Published
- Data as of
The data date records when this dataset was included in the collection. It is separate from the publication date of the source.