How DocuSign cut analytics engineering time in half by pairing Claude Code with dbt v2, dbt MCP, and agent skills
Last edited on Oct 26, 2026
Bishal Gupta, who worked on trusted data products and analytics engineering modernization at DocuSign, shared how far his team has pushed AI into analytics engineering without giving up the controls that keep data trustworthy.
Gupta's starting observation was that SQL generation was never really the bottleneck; context switching was. Engineers were jumping between a Jira requirement, dbt conventions that lived mostly in people's heads, and repeated validation, with no clean handoff between stages of the work.
His fix centers Claude Code as the orchestrator, with dbt Agent Skills supplying project conventions and naming patterns, the dbt MCP server supplying structured metadata and lineage, and dbt v2 validating compiled SQL before a pull request goes out.
Rather than one large agent trying to do everything, Gupta split the workflow into phases, discovery, dbt development, and orchestration, so a failure in one phase (a failed compile, a skipped unit test) gets retried on its own instead of restarting the whole pipeline.
In a live demo, Gupta asked the workflow to build a new quarterly aggregation model, watched it pull in the right dbt Agent Skills and MCP context, generate the model and YAML, compile and validate it against dbt v2, and produce a pull request and matching orchestration job, all with branch isolation and human review still required before anything ships.
Gupta reported a piloted 50 percent productivity gain from requirement to a validated, review-ready dbt asset, along with more consistent naming, testing, and semantic patterns across the team, which let reviewers focus on engineering judgment instead of style fixes. His framing: AI proposes, and engineers stay accountable for what actually merges.
Audience questions focused on guardrails: Gupta described capping test runs at 1,000 rows so an agent couldn't accidentally trigger a billion-row build, and described an early, still-evolving approach to governing which teams' custom skills get layered onto the shared workflow via a master skills file.
Watch every keynote and breakout from dbt Summit 2026 on demand. Watch dbt Summit 2026 on demand →
Get started in dbt
Join the analytics engineers building data infrastructure that actually scales.
Install dbt Wizard CLI
Get started with an agent purpose-built for analytics engineering. It knows which tool to call, which context to pull, and checks its own work before surfacing anything to you.
