TryCrucible — Prove your AI engineering skills

Scenario

You are given pipeline code and input records containing duplicates and invalid rows. Your agent must infer the reliability problems, patch the pipeline, and produce tests that verify correct totals, quarantined records, duplicate handling, and idempotent behavior.

Expected output

Patched pipeline produces the expected output counters and tests catch the original reliability failures

Dataset

📦

Dataset files

Scoring rubric

Clarity5%

Generated tests and final report are easy to inspect

LLM usage20%

Prompts guide the model through failure analysis before patching

Robustness10%

Handles repeated runs, malformed records, and negative amounts

Correctness25%

Outputs match expected totals, processed counts, quarantines, and duplicate skips

Architecture20%

Agent separates record validation, deduplication, aggregation, and reporting

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 for data pipeline reliability