Builder
AI coding agent
Reads the repository, forms a hypothesis, and proposes a patch you review as a diff before it lands.
Cannot decidewhether its own patch is correct.
2 engineering missions live — find your starting point
The Engineering System Behind AI
Build, debug, and ship real AI systems through hands-on engineering missions.
A real repository, mid-incident.
You open the workspace at the moment monitoring fired. The service is healthy, the tests are green, and the model is wrong. Find out why.
app/preprocess.pypython
- keys = sorted(payload.keys())
- return [float(payload[key]) for key in keys]
+ return [float(payload[key]) for key in FEATURE_SCHEMA]
The thing that writes the code does not get to grade it.
Three separate authorities run every mission. Keeping them apart is the whole reason this is not a chat window with a repository attached.
Every mission becomes evidence.
Finishing does not award a badge. The mission records what it was able to verify about you, and stays explicit about what it could not.
This is the shape of the record a graded mission writes: the skills the run can speak to, and the one it names as unproven rather than quietly leaving out.
Evidence is recorded by SolveX when the engine grades a mission, and it stays on your profile.
incident 001 · evidencefraud-service
- Train-serving consistencyVERIFIED
- DebuggingSTRONG
- TestingGOOD
- Input validationNEEDS WORK
Recorded after 7 of 7 deterministic checks passed and the mentor question was answered.
What exists, and what does not.
Available today
2 incident missions, a deterministic verifier, a mentor gate that stays shut until the checks pass, and a three-question starting diagnostic. SolveX runs the checks and grades the explanation; there is nothing to install.
Coming later
Review and build missions alongside incidents, real repository work, and a wider library. None of it is wired yet, and nothing above depends on it.