编程
Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment def...
Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment def...
Generate structured experiment plans that can be logged consistently in experiment tracking systems.
scripts/build_experiment_plan.py to generate consistent run plans.references/tracking-guide.md for reproducibility checklist.Design or audit self-describing ML run metadata attached at initialization, including intent, code and data identity, resume lineage, and evidence limits. Use when wiring a tracker, introducing a run naming pattern, or investigating why a run exists.
Use when operating inside one ALab experiment worktree with that worktree token context to inspect status, edit candidate source, run evaluations, submit fin...
Challenge ML claims with code and falsification
Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define qu...
Build transformer fine-tuning run plans with task settings, hyperparameters, and model-card outputs. Use for repeatable Hugging Face or PyTorch finetuning wo...
Track your AI agent's ROI incrementally — log time saved and direct cash as deliveries happen, then close the cycle monthly with an HTML dashboard.