TryCrucible — Prove your AI engineering skills

AllRAG Pipelines AI Agents MCP Servers Coding Agents Evals & Testing AI Tool Proficiency

// 30 challenges

Build a coding agent that fixes broken Python functions

Build a coding agent that takes a broken Python function, identifies the bug, fixes it, and writes a passing test. The target functions are Python — your agent can be written in any language.

Build a RAG pipeline over a product FAQ

Build a retrieval-augmented generation pipeline that answers customer questions using a provided product FAQ dataset.

Challenges

Build a coding agent that fixes broken Python functions

Build a RAG pipeline over a product FAQ

Build a REST API feature from scratch using AI tools

Build an AI agent that triages customer emails

Build an MCP server for a notes app

Write evals for prompt regression testing

Build a coding agent that fixes failing CI

Build a coding agent that migrates Flask routes to FastAPI

Build a multi-agent research pipeline

Build an MCP server for a REST API with auth and rate limiting

Debug a performance incident using AI tools

Debug a production incident using AI tools only

Extract structured data from multimodal documents

Production RAG with hybrid search and re-ranking

Review and patch security vulnerabilities using AI tools

Write evals for a summarisation model

Write evals for prompt injection defense

Write evals for RAG answer faithfulness

Build a browser automation agent

Build a coding agent for data pipeline reliability

Build a coding agent that writes tests for untested code

Build a multi-hop RAG system for policy questions

Build a RAG pipeline over multi-format documents

Build a read-only SQL MCP server

Build an admin dashboard feature using AI tools

Build an AI agent for calendar scheduling

Build an AI agent that triages GitHub issues

Build an MCP server for filesystem access

Refactor a legacy Python codebase using AI tools

Write evals for a text sentiment classifier