NDL The evaluation layer for AI analytics

Your AI analyst
works today.
Nodal keeps it working.

Your team already asks an agent for numbers. The question isn't whether to deploy AI analytics — it's how to keep the answers right as definitions change, models swap, and usage scales. Nodal watches what gets asked, regression-tests your context on every change, and keeps one governed truth in front of every agent.

Nodal Context is open source — get the repo ↗

§ 01 · The proof

Two agents. One question. One governed answer.

Claude Code on the left, Codex on the right — the same question through the same Nodal context, landing on the same number.

Swap agents without swapping truth. Scale across your organization safely.

Live — Claude Code and Codex answering through the Nodal MCP
§ 02 · The problem

Every failure announces itself.
Except silent SQL.

A query that returns a confident, well-formed, wrong answer and raises no error, no alert, and no objection on its way into a decision.

§ 03 · What Nodal does

Three ways answers go wrong.
One evaluation layer.

The unlock isn't a better model — or a specialized agent. It's governed context, tested like code, in front of every agent your team uses.

§ 04 · Start free

The context layer is open source.

Nodal Context builds governed analytics context with your analyst — interview-built, reviewed by PR, Apache-2.0. Add it to the agent you already use and start there; add evaluation and observability when the team depends on the answers.

Select your agent

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

End of dispatch

Your AI analyst works today. Nodal keeps it working.

Book a demo