All Services

Analyzes up to 200 render job records to flag IQR-based outliers and compute a secondary-measure weighted mean across render_seconds and sample_count fields.

Filters render job records by a numeric interval on render_seconds or sample_count, then produces two analytical reports: an interval-filtered view and adjacent-row change detection.

Filters render job records by a numeric interval on a chosen field and fills missing values using zero, mean, or median imputation — returning two analytical reports for up to 200 rows.

Applies a numeric interval filter and performs a keyed dataset comparison across two supplied render job datasets (render_seconds, sample_count) for up to 200 rows each.

Analyzes render job records by sorting them numerically and computing adjacent-row changes for render_seconds or sample_count fields, returning two analytical reports for up to 200 rows.

Analyzes render job records by computing numeric row ordering and daily sum series for render_seconds or sample_count fields across up to 200 rows.

Sorts render job records by a numeric field and filters them to a specified numeric interval, returning two analytical reports for up to 200 rows.

Ranks render job rows by a numeric field and computes a secondary-measure weighted mean for up to 200 supplied render job records (render_seconds, sample_count).

Analyzes render job records by sorting rows numerically and computing a trailing moving-average series over render_seconds or sample_count, returning two analytical reports for up to 200 rows.

Runs two local analytical reports on render job records — a data quality audit and a base-100 index series — for up to 200 rows of render_seconds or sample_count data.

Runs two local analytical reports on supplied render job records: a record quality audit and category frequency analysis across up to 200 rows of render_seconds and sample_count data.

Analyzes up to 200 render job records (render_seconds, sample_count) and produces two local analytical reports: a record quality audit and a date-by-category pivot table.

Runs two offline analytical reports on render job data: a record quality audit and an equal-width histogram for render_seconds or sample_count fields, across up to 200 rows.

Runs three analytical reports on supplied render job records: record quality audit, exact row deduplication, and adjacent row change detection, for fields render_seconds and sample_count.

Runs three analytical reports on render job records: a record quality audit, exact row deduplication, and a grouped numeric summary of render_seconds or sample_count.

Audits data quality and fills missing values in render job records (render_seconds, sample_count) for up to 200 rows, producing two independent analytical reports.

Audits record quality and compares two keyed datasets of render job metrics (render_seconds, sample_count) for up to 200 rows, returning two independent analytical reports.

Audits record quality and filters rows by a numeric interval for render job datasets containing render_seconds and sample_count fields, returning two analytical reports for up to 200 rows.

Performs a record quality audit and secondary-measure weighted mean analysis on up to 200 render job records with render_seconds and sample_count fields.

Audits record quality and normalises strings in render job data (render_seconds, sample_count) for up to 200 rows, producing 2 independent analytical reports.

Runs three local analytical reports (record quality audit, string normalisation, and adjacent row change detection) on up to 200 render job records containing render_seconds and sample_count fields.

Runs three analytical reports on render job records — a record quality audit, string normalisation, and an equal-width histogram — for up to 200 rows of render_seconds or sample_count data.

Runs three local analytical reports on render job records: a record quality audit, string normalisation, and exact row deduplication — all in a single call.

Audits render job records for quality issues, normalises strings, and fills missing values in render_seconds and sample_count fields for up to 200 rows, returning 3 independent analytical reports.

Runs three local analytical reports on render job records: a record quality audit, string normalisation, and a keyed comparison between two datasets, covering up to 200 rows of render_seconds and sample_count data.

Audits data quality, normalises strings, and orders rows numerically for render job records (render_seconds, sample_count) — up to 200 rows, 3 independent reports per call.

Runs three analytical reports on render job records: a record quality audit, string normalisation, and a secondary-measure weighted mean, for up to 200 rows of render_seconds and sample_count data.

Runs three analytical reports on render job records: data quality audit, string normalisation, and correlation between render_seconds and sample_count — up to 200 rows per call.

Audits data quality and computes two-measure correlation between render_seconds and sample_count for up to 200 render job records, returning two independent analytical reports.

Applies string normalisation and adjacent row change analysis to supplied render job records (render_seconds, sample_count) for up to 200 rows.

Accepts up to 200 render job records and returns two analytical reports: string normalisation of asset/group fields and a daily sum time series for render_seconds or sample_count.

Runs two local analytical reports on render job records: string normalisation and a date-by-category pivot, for up to 200 rows.

Performs string normalisation and duplicate key detection on up to 200 render job records (render_seconds, sample_count), returning two independent analytical reports.

Normalises strings and deduplicates exact rows in render job records (render_seconds, sample_count), producing 2 analytical reports for up to 200 rows.

Normalises string fields and performs keyed row-by-row comparison between two render jobs datasets (render_seconds, sample_count), returning two analytical reports for up to 200 rows.

Normalises string fields and filters render job records by a numeric interval (min/max) on render_seconds or sample_count, returning 2 analytical reports for up to 200 rows.

Normalises string fields and orders rows numerically for up to 200 render job records across two analytical reports covering render_seconds and sample_count.

Performs string normalisation and two-measure Pearson/rank correlation analysis on supplied render job records (render_seconds, sample_count) for up to 200 rows, returning two independent analytical reports.

Computes Pearson correlation between render_seconds and sample_count, plus a weighted mean of the secondary measure, for up to 200 supplied render job records.

Returns a breakdown of academic publication samples on renewable electricity grid integration using Crossref publisher metadata, including DOI references and source attribution.

Returns structured academic citation records (DOIs, publisher metadata, source attribution) on renewable electricity grid integration topics via Crossref.

Retrieves SEC 8-K filing events for a given company ticker or CIK, filtered by date and result limit

Calculates a base-100 rebased index for reorder point values across multiple retail inventory scenarios, enabling relative comparison of reorder triggers.

Accepts an MCP (Model Context Protocol) tool definition and returns content or executes the described tool via the REP web application

Computes a statistical distribution summary for the repeat purchasing customer share metric across supplied retail data rows.

Calculates the gap between a retail store's current repeat-purchasing customer share and a specified target value.

Classifies whether the repeat purchasing customer share ratio falls within a user-defined lower/upper threshold range, using supplied retail figures.

Generates a two-dimensional scenario grid showing how repeat purchasing customer share varies across combinations of repeat_customers and purchasing_customers values.

Returns personalized and aggregate commerce intelligence recommendations based on a specific receipt ID, using paid AI analysis of purchase patterns.

Returns a bundled intelligence payload for a verified receipt, including basket analysis, pricing, recommendations, behavior signals, and product price data.

Returns paid commerce intelligence for a specific receipt, including price-level insights and aggregate commerce data for autonomous agents.

Returns paid commerce intelligence (receipt-level basket analysis, personal spending patterns, and aggregate purchasing trends) for a given receipt ID.

Deduplicates exact rows and fills missing values in replenishment timing records (lead_days, received_units) for up to 200 rows, producing 2 analytical reports.

Computes grouped numeric summaries and numeric row ordering for replenishment timing records (lead_days, received_units) across store groups, returning two analytical reports for up to 200 rows.

Runs two local analytical reports on replenishment timing records — a data quality audit and a numeric row ordering — for up to 200 rows of lead_days/received_units data.

Runs three local analytical reports on replenishment timing rows (lead_days, received_units): a record quality audit, string normalisation, and a base-100 indexed series.

Runs three local analytical reports (record quality audit, string normalisation, and equal-width histogram) on supplied replenishment timing data (lead_days, received_units) for up to 200 rows.

Audits, normalises strings, and fills missing values in replenishment timing records (lead_days, received_units) across up to 200 rows, returning 3 analytical reports.

Inspects structured sample assignments to detect technical/biological replication issues and batch confounding before comparing experimental groups.

Calculates a base-100 rebase index of the burned token fraction (burned/issued ratio) across a series of token supply observations

Computes the local finite-change elasticity of the reported burned token fraction given a baseline token supply and a step percentage.

Calculates and compares reported LP token ownership share between two points in time, returning a deterministic before-and-after verdict.

Computes the local finite-change elasticity of a wallet's reported LP (liquidity-token) ownership share with respect to a small percentage step change in a specified field.

Performs a deterministic ordered trend analysis on a time-series of reported liquidity-token (LP) ownership observations, returning a bounded trend verdict based on caller-supplied data.

Computes a rolling mean of a user's reported LP (liquidity-provider) token ownership share across a series of observations, using a configurable window size.

Computes a two-dimensional scenario grid of reported liquidity-token ownership share across user-defined ranges of owned and total LP units.

Computes benchmark correlation for the reported locked LP-token fraction (locked_lp / total_lp) across a series of observations against a set of benchmark values.

Computes a statistical distribution summary of the locked LP-token fraction (locked_lp / total_lp) across a batch of supplied token observations.

Computes the local finite-change elasticity of the locked LP-token fraction relative to a small step change in a specified LP token field

Compares named scenarios for the reported locked LP-token fraction, computing how changes to locked or total LP token quantities shift the lock-share metric.

Computes a one-input sensitivity table for the reported locked LP-token fraction, sweeping either locked_lp or total_lp across user-supplied values against a baseline.

Ranks a batch of token observations by their locked LP-token fraction (locked_lp / total_lp ratio) using a deterministic calculation.

Computes how changes to locked and total LP-token inputs sequentially attribute to a shift in the locked LP-token fraction (lock share).

Calculates the gap between an observed locked LP-token fraction and a specified target threshold, using supplied token observations.

Computes a two-dimensional scenario grid of the locked LP-token fraction across varying locked_lp and total_lp input combinations, returning deterministic ratio calculations for each cell.

Computes a weighted mean of locked LP-token fractions across multiple token observations, returning a single aggregated result.

Computes a Base-100 rebase index for a series of locked-token-supply observations, expressing each row's locked supply relative to a chosen baseline period.

Computes a before-and-after comparison of reported locked token supply ratios for a given token, returning a deterministic delta report.

Generates a binned distribution histogram of reported locked token supply ratios across a set of token observations.

Calculates the gap between reported locked token supply and a user-defined target, given total and locked token counts.

Classifies reported locked token supply observations against user-defined lower and upper thresholds, returning a deterministic verdict for each row.

Calculates the local finite-change elasticity of reported token holder growth given a baseline holder count and a percentage step size

Calculates the gap between reported token holder growth and a specified target value, returning a deterministic verdict based on supplied holder observations.

Calculates a base-100 rebased index of a token's treasury share ratio across a series of observations, using a deterministic preset engine.

Computes the local finite-change elasticity of a token's treasury share given baseline token supply figures and a perturbation step size.

Ranks a list of token observations by their treasury share (treasury_tokens / total_tokens) using a deterministic calculation.

Computes a sequential before/after attribution analysis showing how changes in treasury tokens and total token supply affect the reported treasury share percentage.

Classifies whether a token's reported treasury share falls within a caller-defined lower/upper threshold range, based on supplied treasury_tokens and total_tokens observations.

Computes the weighted mean of token treasury share ratios (treasury_tokens / total_tokens) across multiple observations using caller-supplied weights.

Computes a Base-100 rebased index of a token's top-holder group share across a time series of supplied observations, anchored to a chosen base row.

Analyzes supplied request latency records to flag IQR outliers and compute correlation between latency_ms and request_count, returning two analytical reports for up to 200 rows.

Normalises latency_ms or request_count strings and flags IQR-based outliers across up to 200 rows of request latency data, producing two analytical reports per call.

Normalises strings and compares two keyed datasets of request latency records (latency_ms, request_count) across up to 200 rows, producing 2 analytical reports.

Returns live PyPI source repository and documentation links for the Python 'requests' package (or any overridden package name).

Identifies which supplied assay references remain pinned to a corrected (superseded) metadata revision, classifying stale links without asserting truth or efficacy.

Computes category frequency distributions and fills missing values (budget_amount or spend_amount) in research grant spending records using zero, mean, or median imputation.

Computes category frequency counts and a secondary-measure weighted mean for research grant spending records (budget_amount, spend_amount) over up to 200 rows.

Deduplicates exact rows and produces grouped numeric summaries for research grant spending records (budget_amount, spend_amount) across up to 200 rows in two independent reports.

Computes a grouped numeric summary and numeric row ordering for up to 200 research grant spending records (budget_amount or spend_amount), returning two analytical reports per call.

Performs string normalisation and two-measure correlation analysis on research grant spending records (budget_amount, spend_amount) for up to 200 rows, returning two independent analytical reports.