See what people ask your AI agents. Check answers against analyst-approved results. Find what changed when a dbt model, business definition, or AI model changes.
For data teams rolling out self-service analytics through AI agents.
Build your context with the free tools ↗Business question
Count distinct customer accounts with a paid subscription at month-end.
Month-end status, or active at any point during the month?
The user reviews the business meaning. The agent runs the query.
People keep using their supported AI tools. Nodal brings the business context to those tools and gives your data team a way to review captured questions and test the answers.
“Paying customers” might mean subscriptions or accounts. Month-end accounts and accounts active at any point in the month can produce different answers. Review the interpretation before the agent queries your warehouse.
Keep model logic and column metadata in dbt. Add the dashboard-level business meaning your analyst confirms.
See the question workflow →A captured answer becomes a verified test only after its reference, time window, and tolerance are approved.
Operate self-service analytics across connected workflows, with the agents and warehouse your team already uses.
Review captured questions, the context used, and gaps in tested coverage.
Compare important answers against analyst-approved references. Keep unchecked answers visible.
Rerun tested questions after dbt, definition, or model changes. Inspect which answers changed.
Give supported agents the same maintained definitions. Keep technical metadata in dbt and add business context above it.
Review a question. Confirm the reference. Keep testing as your stack changes.
Bring the definitions to the supported agents people already use. This side-by-side recording shows Claude Code and Codex answering through the same Nodal context. Agreement is useful; evaluation against an approved reference is how you check correctness.
Nodal Context is optional and Apache-2.0. Already have business context your agents use? Keep it. If you do not, Nodal Context guides an AI interview on your schedule. Each confirmed business definition builds context and a test case together. Compare results with and without context to measure what helped. Keep technical metadata in dbt; add the business meaning above it. Model and warehouse usage are separate.
claude plugin marketplace add nodal-data/nodal-context
claude plugin install nodal-analytics@nodal
codex plugin marketplace add nodal-data/nodal-context
codex plugin add nodal-analytics@nodal
npx skills@latest add nodal-data/nodal-context
Founder, Nodal Data LinkedIn ↗
15+ years leading data science and analytics teams at enterprise scale.
Nodal is the reliability system for AI analytics: it records what agents tell your business, tests those answers against governed ground truth, and alerts your data team when something changes.
About Nodal