From first call to trusted answers in one week.
A SignalPilot engineer or a certified partner works on your schema, under NDA, with nothing leaving your warehouse. You bring one workflow and an hour with your data lead. You leave with a maintained context layer, a passing eval suite, and the cloud agent harness live for one team.
- 1MonScope
- 2TueParse and author
- 3WedReview
- 4ThuEvals and gate
- 5FriShip
- parsed from
- dbt
- semantic layer
- dashboards
- queries
- one workflow · done defined
- 62 definitions drafted · 3 PRs opened
- 12 conflicts settled · approved
- 118 graded questions · gate on
- harness live · eval coverage 91%
Two ways in
Guided, or self-serve.
The integration week
Included on annual Scale and Enterprise plans, billed at list on Team, or delivered by a certified partner.
See pricing →The four-step quickstart
Control plane, warehouse, plugin, MCP gateway, on the open-source stack. Under an hour if your dbt project is clean.
Read the quickstart →What we need from you
Five things, one hour.
Everything runs under NDA. Queries go through the governed gateway and are logged. Bring your own Anthropic, Bedrock, or Vertex key if you prefer.
- Read-only warehouse credentials, or a sandbox schema.
- Access to the dbt repo through the GitHub app, with permission to open pull requests.
- The dashboards your leadership trusts and the queries behind them.
- One recurring workflow and the person who owns it.
- One hour with your data lead on day one, and review time on day three.
A typical week
Scope on Monday. Ship on Friday.
Days are typical, not a contract. A clean dbt project goes faster; a messy one is fixed on the way.
- 01
Day 1 · Scope
Pick the workflow. Walk the schema, dbt models, and dashboards together. Agree on what done looks like.
- 02
Day 2 · Parse and author
Our agents trace how your numbers are calculated. We draft definitions, flag conflicts, and open pull requests where the dbt project needs fixing.
- 03
Day 3 · Review
You approve the definitions and settle the conflicts we found, like two dashboards with different definitions of revenue.
- 04
Day 4 · Evals and gate
Graded questions with failure cases, the nightly run wired, the pull request check turned on.
- 05
Day 5 · Ship
The cloud agent harness goes live for the team, from Claude Cowork, Codex, or Slack. You get the coverage number and the eval report.
What you have at the end
- Approved definitions in dbt, Apache Ossie, and Markdown, in your repo.
- A passing eval suite for the scoped workflow, with the failure cases covered.
- The nightly run and the pull request gate, on.
- The cloud agent harness live for one team, with an evidence graph on every answer.
- A coverage report: models covered, models to do next.
Brightwater Goods · Fri 16:00
- ✓Graded questions118 of 118 passed
- ✓Failure cases caughtfan-out join · refunds left in · wrong window
- ✓Definitions approved62 · 12 conflicts settled · Markdown + Apache Ossie
- ✓Eval coverage91% of models
- ✓Pull request gateon · affected evals rerun on every PR
- ✓Harness liveClaude Cowork · Codex · Slack
- mart_wholesale_margin
- mart_weekly_pipeline
- mart_cohort_retention
- +2 more
After the week
Run it yourself, or hand us the loop.
Your team owns the loop. Thumbs-downs and gaps arrive daily as recommendations, usually as pull requests that add the missing evals or context.
A SignalPilot engineer runs the weekly review and stands behind 90% precision. See Managed →
The next team is the next workflow. With the context layer in place it takes days, not another week.
FAQ
Before you book the week.
Our dbt project is a mess. Does that stop us?
No. Fixing the project is part of the week. We open the pull requests; you review them.
Do we have to replace our BI tool?
No. Definitions ship in the Apache Ossie format so your BI tool can read them too.
Can a partner run the week instead?
Yes. Certified partners deliver the same week on the same tooling.
How much data leaves our warehouse?
Query results reach the sandbox for the answer and its evidence. Definitions live in your repo.
Start the week.
Bring one workflow and your dbt project. We will do the rest.
Open source · Apache 2.0 · GitHub · Slack