TryCrucible — Prove your AI engineering skills

Scenario

You are given 20 feature specifications with acceptance criteria. Pick one and build the feature end-to-end using your AI tool of choice. Submit the code plus your complete AI session transcript.

Expected output

Implementation satisfies all acceptance criteria in the spec, transcript shows structured AI tool usage

Dataset

📦

Dataset files

Scoring rubric

Clarity5%

README explains how to run the endpoint and test it

LLM usage20%

Transcript shows specific prompts, verification steps, and at least one iteration cycle

Robustness10%

Endpoint handles invalid input and server errors gracefully

Correctness25%

Endpoint satisfies all acceptance criteria: correct HTTP methods, request validation, response shape, status codes

Architecture20%

Code is structured appropriately — not a single function, concerns are separated

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 REST API feature from scratch using AI tools