All Services

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.

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

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.

Resizes images to specified dimensions via a paid API endpoint

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.

Splits up to 200 labelled return-reason text records into a grouped train/test dataset partition for local naive-Bayes baseline evaluation.

Identifies low-confidence predictions in a return-reason classifier and returns a prioritized review queue from up to 200 labelled text records.

Checks whether evaluation texts overlap with labeled training records used to classify product return reasons, detecting potential data leakage.

Computes the restock contribution value after processing for returned retail items and reports adjacent period-over-period changes across up to 200 records.

Computes a Base-100 rebased index of net restock value recovered from returned retail units, normalised relative to a chosen baseline row across up to 200 input records.

Computes and compares retail return restock contribution values before and after a change, returning a side-by-side delta report based on supplied figures.

Computes benchmark correlation for retail return restock contribution values across up to 200 records, comparing computed restock values against provided benchmark series.

Computes a distribution histogram of restock contribution values (recovered value minus processing cost) across up to 200 retail return records, bucketed into configurable bins.

Computes a distribution summary of restock value recovered after processing returned retail items, across up to 200 supplied records.

Analyzes retail return restock contribution data for up to 200 records and flags statistical outliers using the interquartile range (IQR) method.

Analyzes ordered trend patterns in retail return restock contribution values across up to 200 records of returned units, recovery rates, inventory value, and processing costs.

Ranks up to 200 retail return records by their restock contribution value, computed from returned units, recoverability, inventory value, and processing cost.

Computes a rolling mean of retail return restock contribution values (recoverable value minus processing cost) over a sliding window of up to 200 supplied rows.

Computes a sequential (waterfall) attribution of how changes in return volume, processing cost, recovery rate, and unit inventory value each contribute to changes in restock value for retail returns.

Calculates the target gap for return restock value after processing, comparing recoverable retail value against a user-supplied target across up to 200 records.

Classifies retail return restock contribution values into threshold bands (above/below user-defined upper and lower bounds) for up to 200 records of returned inventory data.

Generates a two-input scenario grid showing restock value outcomes for retail returns by varying two parameters across user-defined ranges against a baseline.

Searches live public web pages for information about returns management platforms, returning relevant snippets and source links tailored for analyst research.

Validates a funded-task deliverable submission by checking a URL against a canonical task key and returning a claim message for payout

Returns a concrete, evidence-backed repair action for a given website domain as part of a paid micro-audit diagnostic

Returns a diagnostic audit of a website's contact surface, identifying issues and providing a concrete repair action.

Audits a website domain's social search presence and returns evidence-backed findings with a concrete repair action.

Detects exact normalised duplicate text records across up to 200 labelled review-aspect entries (performance, appearance, value, other) and returns a duplicate audit report.

Splits up to 200 labelled review-aspect text records into a grouped train/test dataset split with local evaluation and naive-Bayes baselines.

Runs a grouped three-fold cross-validation using a naive-Bayes classifier on up to 200 labelled review-aspect text records (performance, appearance, value, other) and returns baseline evaluation metrics.

Computes label distribution statistics across up to 200 labelled review-aspect text records (performance, appearance, value, other) using a local naive-Bayes baseline — no hosted model required.

Identifies low-confidence predictions in a naive-Bayes aspect classifier (performance/appearance/value/other) and returns a prioritized queue of records needing human review.

Computes prediction error records for a review aspect classifier (performance/appearance/value/other) given up to 200 labelled text records with predicted probabilities.

Returns a paid AI-generated decision procedure for verifying revenue-share splits against x402 payment receipts in merchant distribution contexts.

Generates a structured RFQ (Request for Quote) body for posting crypto math computation needs to a Demand Board

Search for accommodations by amenities/perks, returning matching lodging options for AI agents via pay-per-request USDC payment.

Fetches and inspects npm registry metadata for the 'rollup' package, surfacing install lifecycle hooks for integration planning and upgrade decisions.

Returns module and type entrypoints from the npm registry metadata for the rollup package, supporting integration and upgrade planning.

Returns runtime and platform constraint metadata for the rollup npm package to support integration and upgrade planning.

Generates a music video using MiniMax AI models and returns the raw video output

Returns a catalog of known AI agent bots for agent SEO and discovery purposes, payable via x402 micropayment

Extracts structured data from web content or documents using autonomous machine agent processing, payable per-call via x402 on Base USDC

Validates and lints an x402 payment manifest for correctness, returning a deterministic result and settlement receipt payable via Base USDC

Retrieves job listing and hiring data for a specific job ID, payable per-request in USDC via x402

Retrieves job listing and hiring data for a specific job by ID, billed per request in USDC via x402

Returns job listings and hiring data matching a specified role, skills, goals, and experience level, paid per request via x402/USDC.

Submits a resume text to receive job listings and hiring data matched to the candidate's profile

Returns job listings and hiring data for a specified role, filtered by goals, skills, and experience level

Search job listings and hiring data by skill or query string, returning structured employment opportunity data

Generates job-related emails (e.g. outreach, follow-up, cover letters) with a specified tone and context for hiring and recruiting workflows

Compares two job offers side-by-side and returns structured hiring/compensation analysis

Analyzes a resume text and returns job-matching or hiring data insights for AI agents, paid per request in USDC via x402

Compares two job offers side-by-side and returns structured hiring/compensation analysis data

Generates a job referral for a target role and company, given the applicant's relationship and achievements

Searches LinkedIn job listings and hiring data based on a job role, skills, and profile attributes, paid per request in USDC via x402

Returns job listing and interview-related hiring data for a specified job title, paid per request via x402/USDC

Returns featured job listings and hiring data for AI agents, paid per request in USDC via x402 protocol

Returns featured job listings and hiring data, paid per request in USDC via x402 protocol

Provides a paid proxy endpoint to retrieve structured data from Figshare, the academic research data sharing platform, at $0.002 per call.