Private AI skills intelligence for people and teams.
Measure, improve, and verify how effectively your team uses AI. Starting with software engineering.
Works with Claude Code, Codex CLI, and Cursor, with analysis running entirely on your machine by default.
- Runs locally
- No code uploaded
- No raw prompts
- Cloud sync: off
Your verification coverage improved but still lags prompt clarity. Try requesting explicit test cases before implementation steps.
Not bossware. A private coach.
BuilderGraph is built for individuals and teams who want honest insight into AI skill, not surveillance tools for employers. Every design decision starts with privacy and consent.
Raw session data stays on your machine. Summaries sync only when you choose. Team dashboards show aggregated patterns, never individual exposure without explicit opt-in.
Privacy principles
- No source-code upload by default
- No raw transcript upload by default
- No full prompt upload by default
- No hidden telemetry
- Cloud sync is opt-in
- Team views are aggregated by default
- Local dashboard binds to 127.0.0.1
- Individual scores not exposed to admins without consent
Private by default. Verifiable when you choose.
Every step is designed around your control, from local analysis to optional cloud sync to public credential sharing.
Scan locally
BuilderGraph CLI reads Claude Code, Codex CLI, and Cursor session history on your machine. Nothing leaves your device by default.
Analyze skill signals
The local engine produces skill scores, prompt quality analysis, iteration patterns, failure detection, and workflow archetypes computed on your hardware.
Review growth recommendations
A private coaching dashboard shows exactly where your AI workflows excel and where targeted improvement will have the most impact.
Optionally sync safe summaries
You choose what, if anything, syncs to BuilderGraph Cloud. Only privacy-preserving skill signals, badge progress, aggregate metrics, and safe evidence summaries are eligible to sync.
Earn badges and verify skills
As BuilderGraph Cloud, Verify, and Challenges come online, you will be able to earn badges and share verification pages on your own terms.
Built to improve real AI work, not just track it.
BuilderGraph surfaces what matters: patterns in how you actually use AI, so you can improve deliberately instead of guessing.
Local session analysis
Scans Claude Code, Codex CLI, and Cursor sessions on-device. Structured metrics extracted without uploading raw content.
Skill scores
Quantified, reproducible scores across prompt clarity, iteration efficiency, verification coverage, context framing, and more.
Failure-pattern detection
Identifies recurring mistakes, inefficient retry loops, and weak hand-off patterns before they become habits.
Prompt and verification analysis
Grades prompt construction quality and whether your AI-assisted work includes meaningful verification steps.
Badges and verification
Earn credentials based on real workflow data and practical challenges. Public verification pages you control.
Team dashboards with privacy defaults
Aggregated, anonymous team-level intelligence by default. Individual scores are never surfaced to admins without explicit consent.
Four parts. One coherent platform.
BuilderGraph ships as a set of composable parts, from local-first CLI to optional cloud infrastructure to public verification.
BuilderGraph Local
Private by design.
CLI and local dashboard that scans AI coding assistant sessions and produces skill metrics, coaching recommendations, and privacy reports entirely on your machine.
BuilderGraph Cloud
Opt-in. Never forced.
Moonwind-hosted SaaS for accounts, workspaces, public profiles, team dashboards, and skill-growth tracking. Activated only when you explicitly choose to sync.
BuilderGraph Verify
Proof you can share.
Public credential and badge verification pages. Share a verified link that proves AI skill level without exposing underlying session data or raw work.
BuilderGraph Challenges
Validate beyond usage.
Practical AI-assisted challenges that validate skills beyond passive usage signals. Structured scenarios that prove you can use AI responsibly, critically, and effectively.
Specific privacy commitments, not marketing language.
Privacy in BuilderGraph isn't a feature toggle added late. It's the default state of every component. Here is exactly what we commit to:
For individuals
Your session data is yours. BuilderGraph acts as a private coach. No employer sees your scores, no platform sells your patterns, no hidden network calls run in the background.
For teams
Team dashboards show aggregated, anonymous patterns. Managers see trend lines and cohort progress, not individual exposure. Individual visibility requires explicit opt-in.
Cloud sync
When you opt into cloud sync, only safe summaries and aggregated metrics transfer. A sync preview shows exactly what would be sent before anything leaves your machine.
Starting with software engineers. Expanding from there.
BuilderGraph starts where AI-assisted work is most measurable today: software engineering workflows with Claude Code, Codex CLI, and Cursor.
Software engineers
Developers using Claude Code, Codex CLI, and Cursor who want honest measurement of how well they leverage AI, and verified proof for employers or clients.
Engineering teams
Teams that want aggregated, privacy-safe intelligence about how AI usage is evolving across the org without surveillance tooling or raw session access.
Future roles
Over time, BuilderGraph can expand to other AI-heavy roles: product, design, analysis, support, operations, and marketing. Starting with software because that's where the signals are richest today.
Build proof of responsible AI skill.
Join the BuilderGraph waitlist and be first to know when local analysis and private skill coaching launch.