All Services

Reads a value from a JSON document at a specified dot-separated path, optimized for research workflows.

Parses a JSON string and returns its root type, top-level keys, and item count, optimized for research workflows.

Compares two string arrays and returns their unique (difference) and shared (intersection) values, optimized for research workflows.

Searches the current web for research methodology sources and links specifically curated for startup founders, returning up to 10 relevant results.

Counts and inventories number tokens (numeric values, figures, and quantitative references) within a research note document supplied as Markdown or plain text.

Normalises whitespace in research note documents (Markdown or plain text, up to 20,000 characters) using deterministic processing without generative AI.

Groups an array of JSON records by a specified field, returning records organized into keyed buckets — tailored for research workflows.

Validates a batch of research records to ensure each one contains all specified required fields, flagging any that are missing.

Computes row-over-row changes in input or recovered mass for research sample recovery records, returning a local descriptive analytics report (up to 200 rows).

Sorts up to 200 research sample recovery records by a chosen numeric field (input_mass_g or recovered_mass_g) and returns a local descriptive analytics report.

Computes a secondary-measure weighted mean over up to 200 research sample recovery records (specimen, date, input_mass_g, recovered_mass_g), returning a single bounded descriptive statistic locally.

Normalises string fields (specimen names, identifiers, dates) across up to 200 research sample recovery records and returns a local descriptive analytics report.

Computes a two-measure correlation (between input_mass_g and recovered_mass_g) over up to 200 research sample recovery records, returning a local descriptive analytics report.

Generates two local analytical reports — a duplicate key report and a daily sum series — for up to 200 rows of research sample data (sample_value or sample_weight).

Analyzes up to 200 research sample rows to produce a duplicate key report and a numeric interval filter report for sample_value or sample_weight fields.

Performs exact row deduplication and Base-100 index series computation on up to 200 research sample records with sample_value and sample_weight fields.

Analyzes up to 200 research sample records by detecting exact duplicate rows and computing a numeric distribution report for a chosen field (sample_value or sample_weight).

Computes two local analytical reports (numeric distribution and date-by-category pivot) on up to 200 supplied research sample rows with sample_value and sample_weight fields.

Runs two local analytical reports — string normalisation and equal-width histogram — on up to 200 supplied research sample records with sample_value and sample_weight fields.

Analyzes research task completion records (completed_tasks, assigned_tasks) by detecting adjacent row changes and filling missing values explicitly, producing two analytical reports for up to 200 rows.

Analyzes research task completion records by computing adjacent row changes and two-measure correlation between completed_tasks and assigned_tasks for up to 200 rows.

Computes a Base-100 indexed time series and a two-measure correlation report for research task completion data (completed_tasks and assigned_tasks) across up to 200 rows.

Computes category frequencies and IQR-based outlier flags for research task completion records (completed_tasks, assigned_tasks) across up to 200 rows, returning 2 independent analytical reports.

Computes category frequencies and a secondary-measure weighted mean from research task completion records (completed_tasks, assigned_tasks) for up to 200 rows, returning two independent analytical reports.

Computes a daily sum time series and a secondary-measure weighted mean for up to 200 rows of research task completion data (completed_tasks, assigned_tasks).

Analyzes up to 200 research task completion records to produce two reports: a duplicate key report and an adjacent row changes report, using local analytical engines.

Analyzes up to 200 research task completion records to produce a duplicate key report and category frequency counts across company groups and dates.

Analyzes up to 200 research task completion records to produce two local analytical reports: a duplicate key report and a numeric distribution for completed_tasks or assigned_tasks.

Deduplicates exact rows and computes adjacent row changes for research task completion records (completed_tasks or assigned_tasks) across up to 200 rows, returning two analytical reports.

Deduplicates supplied research task completion records and generates a Base-100 indexed time series report for completed_tasks or assigned_tasks, covering up to 200 rows in two analytical reports.

Deduplicates exact rows and fills missing values in research task completion records (completed_tasks, assigned_tasks) for up to 200 rows, returning 2 analytical reports.

Performs exact row deduplication and numeric distribution analysis on supplied research task completion records (completed_tasks, assigned_tasks) for up to 200 rows, returning two independent analytical reports.

Computes a grouped numeric summary and a secondary-measure weighted mean for supplied research task completion records (completed_tasks, assigned_tasks) across up to 200 rows, returning two independent analytical reports.

Analyzes supplied research task completion records (completed_tasks, assigned_tasks) by producing a grouped numeric summary and a two-measure correlation report, using local analytical engines on up to 200 rows.

Analyzes up to 200 rows of research task completion records, producing a numeric distribution report and filling missing values in either completed_tasks or assigned_tasks using zero, mean, or median imputation.

Generates two local analytical reports — a numeric distribution and a numeric interval filter — for up to 200 rows of research task completion data (completed_tasks, assigned_tasks).

Analyzes up to 200 research task completion records by filtering rows within a numeric interval and computing adjacent-row changes for completed_tasks or assigned_tasks.

Analyzes supplied research task completion records (completed_tasks, assigned_tasks) by filtering rows to a numeric interval and generating a Base-100 indexed series, producing 2 reports for up to 200 rows.

Applies a numeric interval filter and generates a daily sum time series on up to 200 research task completion records (completed_tasks, assigned_tasks), returning 2 analytical reports.

Filters research task completion records to a numeric interval and fills missing values using zero, mean, or median imputation, producing two analytical reports for up to 200 rows.

Analyzes research task completion records by applying a numeric interval filter and comparing two keyed datasets, returning two analytical reports for up to 200 rows.

Applies a numeric interval filter and computes a trailing mean series on research task completion data (completed_tasks, assigned_tasks) for up to 200 rows, returning two analytical reports.

Produces two analytical reports on research task completion data: numeric row ordering and a daily sum time series, for up to 200 supplied rows.

Generates two local analytical reports — a numeric row ordering and an equal-width histogram — for research task completion data (completed_tasks, assigned_tasks) across up to 200 rows.

Sorts and filters research task completion records (completed_tasks, assigned_tasks) by numeric value, returning up to 2 analytical reports for up to 200 rows.

Ranks research task completion rows numerically and computes a secondary-measure weighted mean across up to 200 supplied records, returning two analytical reports.

Runs three analytical reports (record quality audit, exact row deduplication, and duplicate key report) on up to 200 research task completion records containing completed_tasks and assigned_tasks fields.

Runs three analytical reports on research task completion records: record quality audit, exact row deduplication, and numeric row ordering — all processed locally without external lookups.

Audits research task completion records for data quality issues and produces a numeric row ordering report, returning two independent analytical reports for up to 200 rows.

Audits data quality and computes a secondary-measure weighted mean for research task completion records (completed_tasks and assigned_tasks) across up to 200 rows, delivering two independent analytical reports.

Runs three local analytical reports (record quality audit, string normalisation, and adjacent row changes) on up to 200 research task completion rows containing completed_tasks and assigned_tasks fields.

Runs three local analytical reports on research task completion data: record quality audit, string normalisation, and daily sum series — up to 200 rows, no external lookups.

Audits record quality, normalises strings, and produces a date-by-category pivot for up to 200 research task completion rows (completed_tasks, assigned_tasks) in three independent analytical reports.

Runs three local analytical reports (record quality audit, string normalisation, and duplicate key detection) on up to 200 research task completion records containing completed_tasks and assigned_tasks fields.

Audits data quality, normalises strings, and produces grouped numeric summaries for research task completion records (completed_tasks, assigned_tasks) across up to 200 rows in three independent reports.

Runs three local analytical reports on research task completion records: a record quality audit, string normalisation, and a numeric interval filter for completed_tasks or assigned_tasks fields.

Runs three local analytical reports on research task completion records: a record quality audit, string normalisation, and numeric row ordering for up to 200 rows of completed_tasks and assigned_tasks data.

Audits quality, normalises strings, and computes correlation between completed_tasks and assigned_tasks for up to 200 research task completion records, returning three independent analytical reports.

Computes a secondary-measure weighted mean and performs a keyed dataset comparison on up to 200 rows of research task completion records (completed_tasks, assigned_tasks), returning two independent analytical reports.

Analyzes up to 200 research task completion records, producing two local analytical reports: string normalization of company/group labels and adjacent-row delta computation for completed_tasks or assigned_tasks.

Generates two analytical reports (string normalisation and Base-100 index series) for up to 200 rows of research task completion data (completed_tasks, assigned_tasks).

Runs two local analytical reports on research task completion data: string normalisation of company group labels and a date-by-category pivot table for completed_tasks or assigned_tasks, across up to 200 rows.

Generates two analytical reports (string normalisation and equal-width histogram) on research task completion records (completed_tasks and assigned_tasks) for up to 200 rows.

Normalises string fields and fills missing values in research task completion records (completed_tasks, assigned_tasks) for up to 200 rows, producing 2 analytical reports per call.

Normalises string fields and produces a grouped numeric summary for up to 200 research task completion records (completed_tasks, assigned_tasks) across company groups and dates.

Normalises string fields and performs keyed dataset comparison on two supplied sets of research task completion records (completed_tasks, assigned_tasks) for up to 200 rows each, returning two analytical reports.

Normalises company_group strings and filters completed_tasks/assigned_tasks rows by a numeric min/max interval, producing 2 analytical reports for up to 200 research task completion records.

Computes string normalisation and a trailing mean time series for up to 200 rows of research task completion data (completed_tasks or assigned_tasks), delivered as two independent analytical reports.

Normalises string fields and computes correlation between completed_tasks and assigned_tasks for up to 200 research task completion records, returning two analytical reports.

Computes a trailing moving average series and a two-measure Pearson/rank correlation between completed_tasks and assigned_tasks for up to 200 rows of supplied research task completion data.

Deduplicates exact duplicate rows and computes a trailing moving-average series for supplied reservoir observation records (stored_m3, capacity_m3) — up to 200 rows, two reports per call.

Runs two local analytical reports on up to 200 reservoir observation rows: a record quality audit and a date-by-category pivot, covering stored_m3 and capacity_m3 fields.

Runs two analytical reports on supplied reservoir observation rows: a record quality audit and a grouped numeric summary of stored_m3 or capacity_m3 values, for up to 200 rows.

Runs three analytical reports on reservoir observation records (stored_m3, capacity_m3): record quality audit, string normalisation, and IQR-based outlier detection — no external lookups or predictions.

Runs three analytical reports on supplied reservoir observation records: a record quality audit, string normalisation, and a trailing mean series computation, using local analytical engines with no external lookups.

Runs string normalisation and numeric distribution analysis on up to 200 reservoir observation records (stored_m3, capacity_m3), returning two independent analytical reports.

Resizes images to specified dimensions via a paid API endpoint

Deduplicates exact duplicate rows and produces a date-by-category pivot table from resource booking records (booked_hours, available_hours) for up to 200 rows.

Filters resource booking rows by a numeric interval on booked_hours or available_hours and fills missing values using zero, mean, or median imputation, returning up to 2 analytical reports for up to 200 rows.

Sorts resource booking records by a numeric field and computes an equal-width histogram over booked_hours or available_hours for up to 200 rows.

Runs three analytical reports on resource booking records: record quality audit, string normalisation, and secondary-measure weighted mean — all computed locally on up to 200 supplied rows.

Calculates visitor-to-lead and lead-to-customer conversion rates tailored for retail workflows.

Splits a total monetary budget across multiple retail categories using supplied percentage weights, returning the allocated amount for each percentage.

Searches live public web pages for information about retail point-of-sale integrations aimed at developers, returning source links and snippets.

Searches live public web pages for information about retail point-of-sale integrations relevant to operations teams, returning source links and text snippets.

Searches live public web pages for information about retail point-of-sale integrations targeted at technology buyers, returning source links and snippets.

Computes adjacent period changes for returned goods value recovery rates given supplied retail return and cost figures (up to 200 records).

Computes a Base-100 rebased index series for returned goods value recovery rates from supplied retail return data

Computes and compares before-and-after metrics for retail returned goods value recovery, reporting percentage changes and recovery rate deltas between two periods.

Computes the local finite-change elasticity of a returned goods value recovery metric (recovered_value or returned_goods_cost) given a baseline and a step size, using supplied retail figures only.

Computes a one-input sensitivity table for returned goods value recovery metrics, varying either recovered value or returned goods cost across up to 50 supplied values against a retail baseline.

Calculates the value recovery ratio for a single returned goods scenario given recovered value and original cost.

Classifies retail returned-goods value recovery records as above or below configurable lower/upper thresholds, returning a bounded classification report for up to 200 records.

Computes a weighted mean of the recovery rate (recovered_value / returned_goods_cost) across up to 200 retail return records, using caller-supplied weights.

Computes adjacent period changes in return processing cost per case from supplied retail labour, postage, and other cost data across up to 200 records.

Calculates the return processing cost per case for up to 200 retail records by dividing total costs (labour, postage, other) by number of processed returns.

Performs sequential input-change (waterfall) attribution analysis on retail return processing cost per case, showing how changes in labour, postage, other costs, and volume drive the overall cost difference between two periods.

Generates a two-input scenario grid computing return processing cost per case across combinations of two varying cost/volume inputs against a baseline.

Computes confidence calibration bins for a return-reason classifier, given up to 200 labelled records with predicted probabilities and actual labels.

Audits up to 200 labelled return-reason text records to detect exact normalised duplicates within the supplied dataset.