Nineteen labs.
/ pick an instrument.

Design RAG pipelines, LLM architectures, and agent systems on an interactive canvas. AI evaluates architecture, cost, and trade-offs.

Write and iterate on production prompts. Live eval scoring on output quality, edge cases, and instruction clarity.

Write test cases for AI systems. Run evals, catch regressions, score on coverage and metric quality.

Configure chunking, embeddings, and retrieval for a document corpus. Optimize quality with RAGAS-style metrics.

Define tools and orchestration logic. Test agents against scenarios. Scored on task completion and efficiency.

Implement gradient descent, attention, k-means from scratch in Python. Live execution with test validation.

AI-generated problems, real-time code monitoring, complexity analysis, and solution comparison.

Drag-and-drop canvas with 9 component types. AI evaluates trade-offs, scaling, and reliability.

UML class diagrams with integrated code editor. AI reviews SOLID principles and design patterns.

8 question categories with STAR method coaching. Detailed scoring on structure, impact, and clarity.

Review realistic PRs to find bugs, anti-patterns, security issues, and performance problems.

Find and fix bugs in realistic code with progressive hints and bug-by-bug evaluation.

Design REST APIs for real-world scenarios. Evaluation on naming, error handling, and conventions.

Write queries against realistic schemas. Schema design mode with optimization tips.

Turn-based coding with AI. You write, AI reviews. Progressive feedback each turn.

Merge conflicts, rebasing, shell scripting. Real-world Git scenarios with step-by-step evaluation.

Write Architecture Decision Records. Analyze trade-offs and document reasoning.

Identify N+1 queries, memory leaks, unnecessary re-renders. Frontend & backend scenarios.

Find XSS, SQL injection, auth bypasses. Severity classification with exploit explanations.