NRD Insight uses AI to review every pull request your team merges — grading real engineering craft across 12 dimensions, tying it to business impact, and turning what it finds into growth plans for every developer. Every score backed by a quote from the actual diff.
14 days free · up to 5 repos · nothing analyzed until you say so.
Your code never leaves AWS and is never used to train models.
Install our GitHub App and pick exactly which repos to analyze. Nothing is analyzed until you enable it, repo by repo. Revoke access anytime with one click. Optionally connect Linear to tie code to the roadmap.
Each night, every merged PR and commit is graded against a fixed 12-dimension rubric and 24 engineering principles — inside AWS, with the evidence for every score preserved and auditable.
Dashboards for every developer, team, and repo: strengths, gaps, trajectory, business impact. Plus interactive training programs generated from your team's own code.
The rubric is fixed, versioned, and public to your team — the same bar for everyone. Trivial changes (lockfiles, typos) are filtered out before they cost you anything.
Connect Linear and NRD Insight links every PR to the issue it served — even when nobody remembered to tag it.
Every weakness the analysis finds becomes a concrete, personalized training program — with exercises generated from that developer's actual pull requests, runnable in a sandboxed editor.
We ask for a lot of trust — read access to your code. Here is exactly how we honor it.
Analysis runs on Amazon Bedrock inside our AWS environment. Diffs are stored encrypted (KMS) in S3, transit is TLS everywhere, and your code is never used to train any model.
The GitHub App requests read-only access to contents, pull requests, and metadata — nothing else. You choose the repos. Uninstall revokes everything instantly.
Every row of your data is isolated with Postgres row-level security enforced at the database layer — not just application filters. Your data is invisible to any other customer, by construction.
Every score traces to a stored model response and a quoted diff. When a number surprises you, click through to the exact evidence — no black boxes.
Runs entirely on AWS infrastructure holding SOC 2, ISO 27001, and PCI DSS attestations. Payments are handled by Stripe — card data never touches our servers.
Hard monthly AI-spend caps you configure. Export or delete your data on request. A DPA is available for teams that need one.
A seat is a developer whose code we analyzed that month — viewers, managers, and stakeholders are always free. Every plan includes AI-analysis credits; heavy months can opt in to overage at $0.05/credit, and you can cap spend so an invoice never surprises you.
No. Never. Analysis runs on Amazon Bedrock inside AWS, whose terms prohibit using your inputs to train models. Diffs are processed to produce your scores, stored encrypted for your own audit trail, and used for nothing else.
The fastest way to make engineers hate measurement is to measure motion — commit counts, LOC. We deliberately never rank on volume. Engineers get the same evidence leaders see, their own growth view, and training built from their own code. The rubric is fixed and visible: the same bar for everyone, with receipts.
Read-only: repository contents, pull requests, and metadata on only the repositories you enable. No write access of any kind. Uninstalling the GitHub App severs access immediately.
Only a developer whose code we analyzed in that billing month. Everyone who just views dashboards is free, and your invoice lists exactly which developers were counted.
All of them. The rubric measures engineering judgment — correctness, testing, error handling, design — which the AI evaluates in any language or framework, informed by each repo's own conventions.
Trivial changes are filtered before any AI runs, every plan includes a generous credit allowance, and when it's exhausted analysis pauses (cheap git metrics keep flowing) until you opt in to overage or your period renews. You are structurally protected from surprise bills.
Connected in minutes · first insights by tomorrow morning