AI-assisted Pair Programming
Build application features or debug AI and machine-learning repositories. Edit and test here, work independently, or use your preferred AI assistant in another tab.
34 exercises · Python & JavaScript
Read a supplied Python repository, repair or complete one component, and test your change. Practise independently, without an AI coding assistant.
22 exercises · Read · Debug · Complete · Test
Conway's Game of Life with OOP
Diagnose why a complete-looking Game of Life implementation corrupts a generation while it updates the board.
Open exerciseInbox Safety Cutoff
Trace a working classifier evaluator, predict how its cutoff changes errors, and defend a precision–recall decision.
Open exerciseAlice and Bob Game Engine
Find and repair three subtle state-transition bugs in a working-looking rock-paper-scissors engine.
Open exerciseTrail Arrival Model Review
Build a leakage-safe offline review, compare the current model with a candidate, and check whether aggregate improvement hides a harmful trail segment.
Open exerciseRepair the A/B Test Analyzer
Repair the campaign-level analysis, compare company segments and budget distributions, and return a decision that preserves conflicting business evidence.
Open exerciseBayesian Rate Monitor
Complete focused Beta–Bernoulli updates and reproducible posterior comparison inside an otherwise working model.
Open exerciseValidation Leak Audit
Audit an offline model evaluator for a data leak, repair it so learned preprocessing is fit on the training split only, and restore an honest validation score.
Open exerciseNeighborhood Picks
Diagnose a neighbor-based recommender whose similarity and score calculations produce plausible but incorrect rankings.
Open exerciseMentor Stipend Retention Study
Diagnose a plausible before-after analysis that wrongly attributes a shared retention trend to the mentor stipend.
Open exerciseMarketplace Risk Gate
Repair a real-time risk gate whose time window and decision precedence can silently approve or delay the wrong orders.
Open exerciseMonty Hall: Stay or Switch?
Complete a reproducible simulation, preserve the host’s information rule, and connect the observed win rates to conditional probability.
Open exerciseRepair the Model Ranking Tests
Repair three incorrect pytest expectations, then prove the corrected tests detect broken ranking implementations.
Open exerciseCold-Start Picks
Recommend movies to a brand-new member from a user–movie rating matrix, handling the unrated (None) entries that make the new member cold.
Open exerciseIncident Runbook RAG with LlamaIndex
Complete a LlamaIndex ingestion and retrieval boundary that preserves citations and applies permissions before search.
Open exerciseDebug Report Chunking Before LlamaIndex
Repair the document-cleaning boundary that prepares structured report sections for LlamaIndex.
Open exerciseComplete the CrewAI Tool Guard
Complete the approval and idempotency boundary around a CrewAI crew’s proposed support action.
Open exerciseThe Cache That Must Not Leak
Complete a semantic cache that reuses an answer when a new question means the same thing, and never reuses one across a tenant, model, or prompt version boundary.
Open exerciseThe Tuesday Prompt Tweak
Complete the evaluation harness that scores a candidate by slice and blocks a release when any slice regresses, even while the overall score improves.
Open exerciseRepair the LangChain RAG Tests
Repair tests around LangChain Runnable boundaries, citations, abstention, and customer-scoped history.
Open exerciseDebug a Production Support Proposal Workflow
Debug request deduplication, tenant context, and evidence validation around a supplied CrewAI adapter.
Open exerciseRepair the AI API Reliability Tests
Repair tests for retry classification, idempotency, fallback, and request accounting.
Open exerciseRepair the Production RAG Monitoring Tests
Repair tests for retrieval failures, tenant-level metrics, groundedness alerts, and expected abstention.
Open exercise