CodeTrain: Learn your codebase by writing it

Beta — CodeTrain is early and improving every week. Tell us what to fix or what you wish it did: [email protected].

AI can write the code. It can just as easily take a team off the rails.<br>CodeTrain keeps your engineers on the tracks: they understand what they ship, and you can prove it.

The skill is quietly leaving the building

As AI writes more of the code, the understanding behind it erodes. Juniors ship features they can't debug. Onboarding still takes months. "It works" stops meaning "we know why."

89%<br>of educators report AI-driven skill atrophy<br>The discovery phase of learning, where understanding actually forms, gets skipped when the answer is one tab away.

3–6 months<br>to ramp a new hire on a real codebase<br>Generic courses teach someone else's code. Your patterns, your standards, your gotchas go untaught.

$200k+<br>to replace a developer who never ramped<br>Seniors burn their week answering the same questions. Skill doesn't compound; it leaks.

Learn by doing, on the code that matters

No videos, no toy exercises. A Socratic tutor asks, nudges, reviews what you wrote, and runs the tests, but it never hands you the answer.

Point it at your repo (or a sandbox)<br>Repo mode edits land in your real branch, so finished code is just part of your work. Sandbox mode is a throwaway lesson based on whatever you give/ask the model. Either way it runs on 127.0.0.1 , so your code stays local.

Write each step yourself<br>The tutor breaks the work into tiny steps in a real editor with an instant Run button. You type the line; it reviews what you wrote and explains what changed.

Get nudged, not spoon-fed<br>Stuck? It shrinks the step or reveals the next hint, never the solution. Failing code is the best teaching moment, so it leans in instead of bailing out.

It remembers you<br>A small local profile tracks your level, streak, and recurring gaps, then resurfaces what you struggled with later (spaced repetition). Sync it across machines on Pro.

Not another autocomplete

Your live codebase<br>Trained on your repo and standards, not generic katas (Codecademy, Scrimba) or someone else's curriculum.

You type every line<br>Hands-on by design. Reading an explanation isn't learning; producing the code is. That's the difference from AI explainers.

Local-first by design<br>With the free skill and the codetrain agent your code stays on your machine — only small prompt snippets cross the wire (or, with your own key, nothing but a license check). The managed in-browser tutor sends what you submit; see our privacy policy.

For engineering teams

A free tutor helps one dev. A team needs to standardize and measure understanding. You onboard everyone on your codebase the same way, and you can prove it stuck.

Onboarding that compounds beta<br>Configure your repo, standards, and a safe first task; CodeTrain runs each new hire through an interactive journey to an early win. They ramp in weeks, not months, without tying up your seniors.

See who's ramping<br>A team dashboard shows each member's finished lessons, concepts, and usage at a glance. Per-seat budgets keep spend predictable; bring your own model key for your data on your account. SSO/SCIM, audit logs & self-host are available for Enterprise — talk to us.

Pricing

Start free. Upgrade when you want your real repos, your own model key, or your whole team. No card to start.

Free

$0

Sandbox mode<br>10 sessions / month<br>Local profile + streaks<br>The open-source skill, forever

Start free

Pro · most popular

$24 / mo

Your real repos (repo mode)<br>Fair-use sessions, zero setup<br>Cross-device profile sync<br>Bring your own key (optional)

Get Pro

Team

$32 / seat/mo

Everything in Pro<br>Onboarding journeys (beta)<br>Team usage & progress dashboard<br>Per-seat budgets + central billing<br>Bring your own key

Choose Team

Enterprise

Custom

SSO / SCIM, audit logs<br>VPC / self-host, SOC 2<br>Code never leaves your env<br>Onboarding-ROI pricing

Talk to sales

Questions, answered

Does my code get uploaded anywhere?No. The agent runs on your machine and serves the UI on localhost. On the managed plan, only short prompt snippets go to the model. On Bring-Your-Own-Key (Team/Enterprise), model calls go straight to Anthropic with your key, and nothing but a license check touches our servers.

Isn't this just ChatGPT explaining my code?The opposite. Explainers do the work for you. CodeTrain makes you write every line, reviews it Socratically, runs your tests, and tracks what you didn't get so it can resurface it. You finish able to do it without help.

We already use Copilot / Cursor. Why this too?Those make your team faster at producing code. This makes sure they still understand it, and gives you a way to prove ramp and retention. Different job. They're complements, not competitors.

What does "bring your own key" mean?You connect your own Anthropic (or Bedrock) API key. Your code and prompts go directly to the model on your account. That is best for security and cost control, and we just...