How DocuSign cut analytics engineering time in half by pairing Claude Code with dbt v2, dbt MCP, and agent skills

DocuSign reported that it cut analytics engineering time roughly in half by using Claude Code with dbt v2, dbt MCP, and dbt Agent Skills to automate structured portions of dbt development while retaining human approval. Bishal Gupta identified context switching among requirements, undocumented project conventions, and validation tasks as a larger obstacle than SQL generation itself, and designed a phased workflow for discovery, development, and orchestration that can retry individual failures without restarting the full process. In a demonstration, the system used project context and metadata to create a quarterly aggregation model and YAML, validate compiled SQL, and prepare a pull request and orchestration job with branch isolation. The pilot reportedly improved consistency in naming, testing, and semantic practices while allowing reviewers to focus on engineering decisions, though safeguards such as limiting test runs to 1,000 rows and governing team-specific agent skills remain important areas of development.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.