Somewhere on your team right now, a pull request is getting approved by someone who couldn't rewrite it from scratch. Not because they're lazy. The assistant wrote it, the tests passed, the diff looked plausible, and the sprint doesn't stop for philosophy. Do that for a year and you get a team that ships faster every quarter and understands a little less of its own codebase every quarter too.
I ran into this a few times while building the start of InferHaven. The whole point of this company is that you shouldn't have to hand your code to someone else to get the benefits of AI. But there's a second thing quietly leaving the building, and no firewall catches it: the skill. When the model types and the human tabs through, the knowledge of how your system actually works stops living in your engineers and starts living in a vendor's autocomplete.
So I built the opposite tool. Today I'm launching CodeTrain: a hands-on AI trainer that teaches developers on their own codebase, and refuses to write the code for them.
**The learner writes every line. CodeTrain plans the lesson, sets up each step, runs your code, and grades the result, but it will not type your solution. Not even a "tiny" one-liner. When you're stuck it shrinks the step or gives you a sharper hint. It does not give you the answer, because the answer was never the point.
What a lesson actually looks like
You ask CodeTrain something real. "Walk me through adding a health check to this Dockerfile." "I don't actually understand our retry logic, teach it to me." It breaks that into a short lesson, usually two to six steps, each one small enough to hold in your head.
Each step is one concrete thing to write in a syntax-highlighted editor with a Run button. You type it. The code executes immediately: Python and JavaScript run right in your browser, shell and a few other runtimes run in an isolated sandbox, web stuff renders in a live preview. Then the tutor reviews what you wrote against the step's criteria, shows you ✓ and ✗ per criterion, and either advances you or asks the question that makes you see what's off. Fail a step multiple times and it doesn't dump the solution on you. It cuts the step in half.
$ codetrain start --mode repo
Session a6502084e8254276a394d5be578e9229 started (repo mode).
Plan: team
Modes: sandbox, repo
Sessions: 0/1000 this month
Usage: 0% of your monthly allowance (100% left)
Models: haiku, sonnet
Your tutor is open in the browser:
http://127.0.0.1:7341
(workspace: /tmp/codetrain-repo-v555lhi7/repo)
Tutoring is live in your browser — keep this window open. Ctrl-C to stop.
Before the lesson: pick your level, how much help you want, and whether the session may build toward a real edit. The goal here is the health check from the terminal above.
That's repo mode, the paid tier. The tutor reads your actual repository, builds lessons out of your actual code, and at the end of a guided lesson (can run exploration only if desired) it proposes one integrated patch that lands the code you wrote onto your real branch. You review it like any other diff. Free tier does not include repo mode and drops you into sandbox practice instead: same tutor, same you-type-it rule, generated exercises from natural language.
Here is that health-check lesson, start to finish. Step 2 has you draft the probe on a scratch Dockerfile where mistakes are free:
You write the HEALTHCHECK on scratch first. Run gives you the linter, Send gives you the tutor's verdict against the step's criteria.
Step 3 moves the line you wrote into the real Dockerfile, all 360-odd lines of it, in the one spot where Docker will actually honour it:
Same instruction, real file. Placement is the lesson here: Docker only honours the last HEALTHCHECK, so it goes right before ENTRYPOINT/CMD.
Pass the final step and the tutor offers the one targeted patch it guided you on: the diff of what you typed, applied to your working tree only after you approve it.
Every criterion checked, then the patch-back: your change as a reviewable diff. A .codetrain.bak backup is saved before anything is written.
Change shipped. A real HEALTHCHECK lives in the repo, and the recap lists what you practiced, not what was generated for you.
This is not another assistant
Don't get me wrong. I use coding assistants daily and they're great at their job. Their job is producing code. CodeTrain's job is producing engineers who understand code, and those jobs basically pull in opposite directions.
| AI assistant (Cursor, Copilot, Claude Code) | CodeTrain |
|---|---|
| You describe, it writes | It plans tiny steps, you write them |
| Output: working code, fast | Output: a developer who gets it |
| Understanding is optional | Understanding is graded, per step |
| Great when shipping is the goal | Great when the goal is your team |
Use both. Seriously. Let the assistant ship the sprint while CodeTrain makes sure the person accepting its diffs could have written them.
"Code got cheap. Understanding didn't. Train the part that's still expensive."
An InferHaven product
InferHaven exists because your code is yours and should stay on your hardware. CodeTrain extends the same instinct to where your code lives secondly: wetware, brains, good ol' humans. Keep the code in-house, keep the skill in-house with it.
It's built the way you'd expect from us. The agent runs on your machine. Sandbox lessons execute in your browser, not on a stranger's box. Repo mode works against your local checkout. And if you'd rather run lessons through your own model account, bring your own key: Anthropic, OpenRouter, Bedrock, Vertex, or even an Ollama endpoint you host yourself!
What it costs, honestly
The free tier is real: the in-browser trainer, ten sessions a month, streaks and progress tracking, no credit card. It's capped because every managed session costs us actual inference money.
Pro is $24/month and adds repo mode on your real projects, fair-use session limits, sync across devices, and optional BYOK. Team is $32 per seat and adds the part managers keep asking me about: a dashboard showing who's ramping, per-seat budgets, central billing, and onboarding journeys for new hires. Enterprise is the usual conversation about SSO and code that can't leave your network. If that's you, sales@codetrain.ai.
Go type something
CodeTrain is live at codetrain.ai. Sign in, ask it to teach you something you've been faking your way around, and see how it feels to be the one controlling the keyboard again. There's a one-minute demo on the landing page if you want to watch before you commit to the free tier's grand total of... zero dollars.
InferHaven keeps your code yours. CodeTrain keeps the skill yours. Same haven, different cargo. The beacon is active!
— Ethan L.
This is cross-posted from the InferHaven blog. I'm the founder and I'll be in the comments; if you try a lesson and it teaches you something wrong or hands you the answer on a silver platter, I want to hear about it more than I want the compliments.
Top comments (0)