DATACLAW-AGENT

Author and publish bespoke analytical reports from validated findings, bounded aggregate evidence, methodology, caveats, and an evidence ledger. Use for final reports, report-like dashboards, interactive analytical briefings, or redesigning existing report HTML; the creative author owns all unspecified story, prose, layout, and visual decisions.

Use Dataclaw tools for governed data science and analytics work. Includes tools for interacting with data, running jupyter notebooks, proposing, updating and reviewing analytical plans, experiment tracking, training machine learning models, and generating reports.

Publish, revise, inspect, export, and troubleshoot DataClaw artifacts. Use when a report, dashboard, chart, profile, model card, or living-report note should become a secure, versioned, shareable artifact through dataclaw-artifacts.

Estimate and defend causal effects inside the Dataclaw data-science workflow by choosing an identification strategy, stating the estimand, testing design-specific assumptions, quantifying uncertainty, and refusing unsupported causal claims. Use for impact analysis, policy or treatment effects, difference-in-differences, matching or weighting, instrumental variables, regression discontinuity, synthetic controls, interrupted time series, mediation questions, and observational “does X cause Y?” requests.

Design, analyze, or audit randomized experiments inside the Dataclaw data-science workflow with a defensible randomization unit, power and duration, pre-registered outcomes, assignment and exposure checks, sequential and multiplicity control, and uncertainty at the assignment level. Use for A/B and multivariate tests, cluster or geo experiments, switchbacks, holdouts, factorial designs, non-inferiority, uplift and heterogeneous-treatment analyses, experiment readouts, and sample-size planning.

Build reproducible, leakage-safe model inputs inside the Dataclaw data-science workflow by defining prediction-time availability, excluding identifiers, fitting transforms within folds, cross-fitting target-derived features, handling temporal and grouped data correctly, and versioning feature lineage. Use for tabular, temporal, categorical, text, geospatial, nested, interaction, aggregation, embedding, selection, and dimensionality-reduction features used by predictive, forecasting, causal, uplift, or segmentation models.

Build, evaluate, calibrate, and operationalize supervised prediction models inside the Dataclaw data-science workflow with leakage-safe validation, decision-aligned metrics and thresholds, honest baselines, subgroup and shift checks, uncertainty, and deployment monitoring. Use for classification, regression, ranking, propensity or risk scores, churn and fraud prediction, lead scoring, probability calibration, model comparison, model cards, and audits of existing predictive systems.

Segment a population into decision-serving groups inside the Dataclaw data-science workflow — pick the segmentation type from the decision, build a leakage-safe feature space, cluster by data shape, prove the segments are stable and separable rather than noise, then profile and operationalize them with a typing model. Use for customer, market, audience, account, patient, and HCP segmentation, RFM and value/CLV tiers, needs-based and attitudinal personas, behavioral and journey clustering, k-means / GMM / HDBSCAN / latent-class methods, mixed-type and high-dimensional segmentation, and uplift / persuadable targeting.

Forecast business time series inside the Dataclaw data-science workflow — frame the decision, run leakage-safe rolling-origin backtests against naive baselines, select and generate calibrated time-series forecasts, and run conditional scenarios. Use for demand, revenue, traffic, usage, cost, intermittent or hierarchical series, regressor- or event-driven forecasts, forecast review, and scenario planning.

Run goal-directed exploratory data analysis tailored to the user's question, domain, unit of observation, problem type, data types, quality risks, and relationship/correlation structure.

Analyze survey, poll, questionnaire, tracker, and panel data inside the Dataclaw data-science workflow — pin the sample design and question bases, screen quality, estimate weighted toplines and crosstabs with design-based variance, compare groups and waves correctly, run drivers/segmentation/factor work, and code open-text verbatims under governance. Use for Google Forms, SurveyMonkey, Qualtrics, or SPSS/CSV/Parquet survey data, NPS and Likert and multi-select analysis, weighted and unweighted results, and evidence-bound survey reporting.

Review DataClaw analysis outputs against structured evidence, hypotheses, findings, gates, and artifact metadata.

Quick dataset profiling for compact schema, summary statistics, missingness, duplicates, distributions, and obvious quality checks. For goal-directed or domain-sensitive EDA, use structured_eda instead.

Create trustworthy notebook and chat visuals and prepare bounded, well-described aggregate evidence for report_design. Use for analytical charting, visual integrity checks, or packaging visual evidence; do not use it to choose a final report layout or component system.