TryCrucible — Prove your AI engineering skills

Scenario

You are given 15 incident packages: error logs, stack traces, relevant source files, and metrics. Pick one of the 5 test incidents and identify the root cause, the exact line of code responsible, and the fix. Submit your analysis plus AI tool transcript.

Expected output

Root cause is correct, responsible code location is identified, proposed fix is valid

Dataset

📦

Dataset files

Scoring rubric

Clarity5%

Incident report is structured: symptoms, hypothesis, evidence, conclusion, fix

LLM usage20%

Transcript shows the model being guided through evidence, not just asked for an answer

Robustness10%

Analysis acknowledges uncertainty where logs are ambiguous rather than guessing confidently

Correctness25%

Root cause matches ground truth, responsible line is within 5 lines of actual bug, fix is syntactically valid

Architecture20%

Debugging approach is systematic — hypothesis generation before conclusion

Language-free evaluation

Build your solution in any language or framework — Python, TypeScript, Go, Rust, Java, C#, or anything else. The dataset artifacts may be in one language; your implementation does not need to match. TryCrucible evaluates the behaviour of your system, the quality of your AI workflow, your verification strategy, and the reproducibility of your submission — not your language choice.

Submission requirements

A public GitHub repository link
A Dockerfile in the repo root — any language or framework; the evaluator builds and runs your container
Your solution reads test_inputs.json from the working directory and writes results.json — standard I/O contract across all challenges
A decisions.md — 3–5 sentences on the key architectural and AI-workflow choices you made
The system must be fully reproducible — we clone, build, and run it against real test inputs

Evaluation contract

When you submit, the evaluator runs these steps in order:

1Clone your public GitHub repository
2Build your container from the Dockerfile in the repo root
3Mount test_inputs.json into the working directory
4Run your solution in a network-isolated sandbox (5 min limit, 512 MB RAM)
5Read results.json from the working directory
6Score correctness against hidden ground truth, then score architecture, AI workflow, robustness, and clarity

// I/O contract — same schema for every challenge

Input (provided by evaluator)

// test_inputs.json
[
  { "id": "t1", "input": { ... } },
  { "id": "t2", "input": { ... } }
]

Output (written by your solution)

Create a free account to start

Already have one? Sign in

Debug a production incident using AI tools only