Data & Analytics

Design a hyperparameter tuning strategy for a model — search space, method, and budget. Use when asked to "tune hyperparameters", "define a search space", or "set a tuning budget".

Design a model training pipeline — algorithm selection, cross-validation, and serialization. Use when asked to "train a model for this", "design a training pipeline", or "which algorithm should we use".

Audit existing model training code — find reproducibility issues, data leakage, and missing best practices. Use when asked to "audit our training code", "is our training reproducible", or "check for training data leakage".

Design or audit a feature store — serving, freshness, and sharing across models. Use when asked "do we need a feature store", "design a feature store", or "share features across models".

Audit feature engineering code for leakage, quality issues, and pipeline correctness. Use when asked to "audit our feature pipeline", "is there data leakage", or "find feature quality issues".

Design and implement a feature engineering pipeline for a ML problem. Use when asked to "engineer features for this model", "what features should we build", or "design feature transformations".

Design eval harnesses — task schemas, metrics, dataset versioning, eval-as-code patterns. Use when asked to "build an eval harness", "set up eval-as-code", or "version our eval datasets".

Design an LLM eval — task schema, scoring rubric, dataset composition, and pass/fail thresholds. Use when asked to "design an LLM eval", "write a scoring rubric", or "how do we measure this model".

Audit existing experimentation infrastructure and past experiments for methodology issues. Use when asked to "audit our experiments", "is our experimentation sound", or "review past test methodology".

Analyze A/B test results — statistical significance, practical significance, and segmentation. Use when asked to "analyze our A/B test", "is this result significant", or "read these experiment results".

Audit existing ML monitoring — find gaps in drift coverage and missing alerts. Use when asked to "audit our ML monitoring", "are our models monitored", or "find drift coverage gaps".

Design a drift monitoring system for a production ML model. Use when asked to "monitor this model in production", "detect data drift", or "set up ML monitoring".

Design drift alerts and escalation — thresholds, runbooks, and retrain triggers. Use when asked to "alert on model drift", "when should we retrain", or "write a drift escalation runbook".

Build an ML pipeline — from data to trained model to serving endpoint. Use when asked to "build ML model", "train a model", "prediction pipeline", "classification", or "regression".

Design a data validation pipeline — schema checks, range validation, and quality metrics. Use when asked to "validate incoming data", "add schema checks", or "define data quality metrics".

Design a data cleaning and transformation pipeline — missing values, outliers, and deduplication. Use when asked to "clean this dataset", "handle missing values", or "deduplicate this data".

Audit existing data cleaning code — find missing validation, silent data loss, and quality gaps. Use when asked to "audit our data cleaning", "are we losing data silently", or "find data quality gaps".

Validate and benchmark a forecasting model — walk-forward CV, error metrics, baseline comparison. Use when asked "is this forecast any good", "validate a forecasting model", or "backtest the forecast".

Survey existing forecasting code or models in a codebase — find gaps, stale models, and missing validation. Use when asked "what forecasting models do we have", "audit our forecasts", or "find stale models".

Build a forecasting model for a time series — demand, revenue, or usage prediction. Use when asked to "forecast demand", "predict next quarter revenue", or "build a time series model".

Map AI cost topology — billing attribution, team-level spend, forecast vs actuals, alert gaps. Use when asked to "map our AI spend", "who is spending on LLMs", or "set up AI cost attribution".

Audit AI spend — per-model cost breakdown, top consumers, waste identification, optimization levers. Use when asked "why is our AI bill so high", "audit LLM spend", or "where is our token waste".

Data analysis, visualization, and storytelling for financial, SaaS, and RevOps contexts. Use when analyzing revenue, forecasts, cohorts, churn, pipelines, dashboards, messy data, analytical claims, spreadsheets, or PDFs.

Gated protein design campaign: each expert judgement is a checkpoint a human signs off before compute is spent. Branches: de novo binder design (epitope choice, generation, co-folding ensemble ranking, ranked order sheet); structure and complex prediction with calibrated confidence; protein engineering (stability, enzyme, interface). Fires on designing binders or miniproteins, picking an epitope or hotspots, running RFdiffusion, BindCraft, BoltzGen, ProteinMPNN, ESMFold2 or Protenix, computin...