TryCrucible — Prove your AI engineering skills

Scenario

You are given Python repositories with failing test logs. Your agent must inspect the files, infer the root cause from CI output, patch the bug, and ensure the relevant tests pass. The repos and tests are Python; the agent implementing the fix loop can be written in any language.

Expected output

Agent patches the correct file, explains the root cause, and produces tests that catch the original failure

Dataset

📦

Dataset files

Scoring rubric

Clarity5%

Final report includes failure, root cause, patch summary, and verification result

LLM usage20%

Prompts use the CI evidence and avoid blind rewrites

Robustness10%

Handles misleading logs, multiple files, and boundary cases

Correctness25%

Patch fixes the failing CI case and preserves or adds meaningful tests

Architecture20%

Agent workflow separates log analysis, code inspection, patching, and verification

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

Build a coding agent that fixes failing CI