This guide contains one section for each of the add-in's key functionality areas, followed by a reference guide to all the Excel functions available in the add-in.
Looking to quickly get started? Each section starts with a "quickstart" guide.
Looking for a specific excel function? Use the search box in the table of contents on the left.
XLKitLearn is compatible with Excel for Windows, Mac, and the web. In Excel, open Home → Add-ins → More Add-ins, search for XLKitLearn, and add it to your workbook.
Fit and compare predictive models, evaluate their performance, and score new observations directly from Excel.
Are you currently taking CBS's Business Analytics core class? That class does not use XLKitLearn's Predict module—instead, it directly uses XLKitLearn's machine-learning prediction functions. Click here for details.
Imagine you run a pizza shop and want to give customers more accurate delivery estimates. In this quickstart, you'll use XLKitLearn's Predict module to learn from 100 completed orders and estimate delivery times based on distance, order size, rain, time of day, and driver experience. Along the way, you'll train and evaluate a model, then use it to predict delivery times for new orders. Follow along with the steps below...
A1:F101, including the header row. The predict module always requires you to select the header rows, so that it knows what your column names are.outcome ~ predictors.delivery_minutes ~ . The dot means “use every other column”, so this formula tells XLKitLearn to predict delivery times using every other column in the data.delivery_minutes ~ distance_km + num_pizzas + rain.F1 and type =XKL.PREDICT( to invoke XLKitLearn's prediction function. It accepts two arguments - the first is the model object, which is on the Pizza Model sheet, in cell D10. The second is the new data, which is on this sheet in cells A1:E6. Once you have typed in or selected those ranges as in the screenshot above, type ) to close the function call, and press User manual coming soon
User manual coming soon
User manual coming soon
The list below is a comprehensive list of every function in the add-in. Use the search on the left to filter these functions.
Fit reusable models and use them to generate predictions for new data.
Fit a linear regression model from a table and either a formula or an outcome-column name. Returns a reusable model with a complete coefficient table in its coefficients property.
Training data including a header row. Column names are used by the formula.
A model formula such as y ~ x1 + x2, or just the outcome-column name to use every other column as a predictor.
Returns an XLKitLearn Model entity with a complete coefficient table that is accessible through its coefficients property.
Paste the contents of your clipboard into Cell A1 of a worksheet
Fit a logistic regression model from a table and either a formula or an outcome-column name. The outcome must contain at most two distinct values, and every value must be the number 0 or 1.
Training data including a header row. Column names are used by the formula.
A model formula such as y ~ x1 + x2, or just the outcome-column name to use every other column as a predictor.
Returns an XLKitLearn Model entity with a complete coefficient table that is accessible through its coefficients property.
Paste the contents of your clipboard into Cell A1 of a worksheet
Fit a k-nearest-neighbors model from a table and either a formula or an outcome-column name. Numeric outcomes produce a regressor and nonnumeric outcomes produce a classifier.
Training data including a header row. Column names are used by the formula.
A model formula such as y ~ x1 + x2, or just the outcome-column name to use every other column as a predictor.
The positive whole number of nearest neighbors to use.
Optional training-data row to leave out of the fitted model. Row 1 is the first row after the header.
Returns an XLKitLearn Model entity that can be passed to predict.
Paste the contents of your clipboard into Cell A1 of a worksheet
Evaluate model performance, inspect classification results, and transform data for modeling and visualization.
Calculate the coefficient of determination (R-squared) using scikit-learn's r2_score.
A row or column containing the observed numeric values.
A row or column containing the predicted numeric values, in the same observation order as y_true.
Returns the same R-squared value as sklearn.metrics.r2_score.
Paste the contents of your clipboard into Cell A1 of a worksheet
Calculate root mean squared error using scikit-learn's mean_squared_error.
A row or column containing the observed numeric values.
A row or column containing the predicted numeric values, in the same observation order as y_true.
Returns the square root of sklearn.metrics.mean_squared_error.
Paste the contents of your clipboard into Cell A1 of a worksheet
Calculate binary or multiclass ROC AUC using scikit-learn. Class labels are converted to text and sorted in ascending Python string order, matching XLKitLearn model fitting. For binary data, a score vector must contain the probability of the second (larger) class in that sorted order. For a probability table, columns must follow the complete sorted class order. Multiclass AUC uses one-vs-one averaging.
A row or column containing the observed class labels.
Either one probability per observation for the larger of two sorted classes, or a probability table with one row per observation and one column per class in ascending Python string-sort order.
Returns the same binary ROC AUC or one-vs-one multiclass ROC AUC as sklearn.metrics.roc_auc_score.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create a confusion matrix from observed and predicted class labels. Labels are converted to text and sorted in ascending order.
A row or column containing the observed class labels.
A row or column containing the predicted class labels, in the same observation order as y_true.
Returns a table whose rows are observed classes, columns are predicted classes, and cells contain observation counts.
Paste the contents of your clipboard into Cell A1 of a worksheet
Calculate a binary ROC curve from observed class labels and prediction scores, using at most 20 distinct score thresholds.
A row or column containing the observed labels for exactly two classes.
A row or column containing the predicted probability or score for the second class in ascending string-sort order.
Returns a two-column table headed False positive rate and True positive rate.
Paste the contents of your clipboard into Cell A1 of a worksheet
Use an XLKitLearn model entity to make predictions for new rows of data. The input data should include column headers matching the variables the model was trained on.
XLKitLearn Model entity returned by fitLinearRegression or by the main XLKitLearn modeling workflow.
Rows to score, including a header row. Use the same feature column names and compatible data types as the training data.
Returns a spilled prediction table with a header row. Regression output is headed Prediction; classification output is headed by the model's class levels.
Paste the contents of your clipboard into Cell A1 of a worksheet
Perform multidimensional scaling (MDS) to reduce high-dimensional numeric data to two dimensions. Use this to create coordinates for visualizing similarity or distance among rows.
Numeric data to reduce, with one row per item and one column per original dimension. Do not include headers.
Optional random seed for reproducible coordinates. Defaults to 123.
The number of random initializations to try
Returns a two-column spilled matrix of MDS coordinates, one row per input row.
Paste the contents of your clipboard into Cell A1 of a worksheet
Calculate the sigmoid of a number 1 / (1 + exp(-x))
The number to calculate the sigmoid of
Returns the sigmoid of the numbers input
Paste the contents of your clipboard into Cell A1 of a worksheet
Send prompts to language models and create embeddings through OpenRouter.
Ask a model from OpenRouter to respond to a prompt, continue from a previous LLM Output entity, call workbook tools, or return a structured response. New model calls require Click to run from the GenAI tab.
Prompt or conversation context. Pass a single cell for one prompt, or a vertical range containing prompt text and prior LLM Output entities to continue a conversation.
Optional OpenRouter model ID or alias. Leave blank to use openrouter/auto. Supported aliases include chatgpt, claude, gemini, grok, and deepseek; full IDs from the OpenRouter model list also work.
Optional range of LLM Tool entities created by functions such as sqlTool, runPythonTool, sendEmailTool, or googleMapsPlacesSearchTool. Tools cannot be used in the same call as response_format.
Optional structured output format. Pass one or more Response format field entities from getResponseFormatField, or pass one of the simple strings integer, boolean, or number. Cannot be used in the same call as tools.
Reasoning effort for models that support it. Use higher effort for harder analysis and lower or none for faster, cheaper simple tasks.
Sampling temperature between 0 and 2. Lower values are more focused and repeatable; higher values are more varied. Defaults to the model/provider behavior.
Optional maximum number of output tokens to generate. Some models do not support this parameter. Default value will be 5000.
TRUE to automatically run any tool calls returned by the model. FALSE to return Tool Call entities in the .tool_calls table so you can run each call manually with its corresponding Tool function.
Returns an LLM Output entity. Use dot notation to pull these fields into cells:
Content: the model's text response.tool_calls: a table of function names, IDs, and Tool Call entitiesfield_<field name>: each named structured-output valuellm callFor large outputs, inspect the entity in the side bar.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an embedding vector for text, or for an image when the chosen embedding model supports images. This function is staged when it would make a new model call: after the formula shows Ready to run, select it and click Run staged cells in selection in the GenAI tab of the side bar.
Text to embed, or an Excel image entity when using an image-capable embedding model.
Embedding model to use. Leave blank or use openai for openai/text-embedding-3-small; use gemini for google/gemini-embedding-2-preview; or provide another OpenRouter embeddings model ID.
Returns an Embedding entity with token count, cost, timing, model/provider metadata, and a hidden Embedding value. Use dot notation on the returned entity to spill the numeric vector for similarity search, clustering, or downstream modeling.
Paste the contents of your clipboard into Cell A1 of a worksheet
Define structured responses, inspect tokenization, and analyze token probabilities.
Create one named field for a structured LLM response. Use this helper when you want llm to return predictable fields instead of free-form text: create one field per value you want back, then pass the resulting cells to the response_format argument of llm.
Short field name to use in the structured output. Keep it simple, unique, and spreadsheet-friendly, for example category, score, or reasons.
Data type the model should return for this field: integer, number, string, or boolean.
Plain-language instruction for the model explaining what belongs in this field. Be specific about units, allowed values, and how to handle uncertainty.
TRUE if this field should contain a list of values. Leave blank or FALSE for a single value.
Returns a Response format field entity. Pass one or more of these entities into llm as response_format; use the shorter strings integer, number, or boolean when you only need one simple scalar output.
Paste the contents of your clipboard into Cell A1 of a worksheet
Split text into model-style tokens using the local cl100k_base tokenizer. This is useful for estimating prompt length, inspecting how text is tokenized, or teaching tokenization behavior without making an API call.
Text, number, or boolean value to tokenize. It is converted to text before tokenization.
Returns a single spilled row containing one decoded token per column.
Paste the contents of your clipboard into Cell A1 of a worksheet
Generate up to 100 tokens with GPT-4.1 and show token-by-token probability alternatives. This function is staged when it would make a new model call: after the formula shows Ready to run, select it and click Run staged cells in selection in the GenAI tab of the side bar.
Single prompt to send to the model. Use plain text, a number, or a boolean; conversation entities and ranges are not supported here.
Returns a formatted spill range. The left columns contain prompt, completion, model, provider, date, cache status, token usage, and cost; the remaining columns show each selected output token and the top alternative tokens with probabilities.
Paste the contents of your clipboard into Cell A1 of a worksheet
Connect language models and worksheets to messaging, email, Python, SQL, maps, weather, market data, flights, and location services.
Send a US SMS text message from the workbook. This function is staged for safety: after entering the formula, the cell shows Ready to run; select it and click Run staged cells in selection in the GenAI tab of the side bar to actually send the message.
Recipient phone number in US E.164 format: +1 followed by 10 digits, for example +12125551234.
Message body to send. Use ASCII text only; common smart quotes and dashes are normalized, and the final message must be 159 characters or less.
TRUE to wait up to about 3 minutes for the first reply before returning. Leave blank or FALSE to return as soon as the text is sent.
Returns a Text message entity containing the text ID, recipient, message, and optionally the first reply or a reply-timeout flag. Use getTextResponses later with the text ID to check for additional replies.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm send SMS text messages. Pass the returned LLM Tool entity into the tools argument of llm; the model can then call sendText when it has the recipient number and message.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that sendText call instead of returning a tool descriptor.
Returns an LLM Tool entity. The tool requires a US +1 phone number and a message, and supports an optional wait-for-reply flag.
Paste the contents of your clipboard into Cell A1 of a worksheet
Fetch replies received for a previously sent text message. Use the text ID returned by sendText; this is useful when you sent without waiting, or when you want to check for later replies.
Text ID returned by sendText.
Returns a Text responses entity. In Excel, the card lists replies and exposes a hidden Responses table that can be pulled out with dot notation; outside Excel it returns a JSON array of response strings.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm look up replies to a sent text message. Pass this LLM Tool entity into the tools argument of llm when the model may need to check a conversation by text ID.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that getTextResponses call instead of returning a tool descriptor.
Returns an LLM Tool entity for retrieving SMS replies by text ID.
Paste the contents of your clipboard into Cell A1 of a worksheet
Send an email from the workbook, optionally continuing an existing thread and optionally waiting for a reply. This function is staged for safety: after entering the formula, select the Ready to run cell and click Run staged cells in selection in the GenAI tab of the side bar to actually send the email.
Recipient email address.
Subject line. If left blank, the message is sent with (no subject).
Body text of the email. If left blank, the message body is (no message).
TRUE to wait up to about 3 minutes for a reply before returning. Leave blank or FALSE to return as soon as the email is sent.
Optional thread token from a previous sendEmail result. Provide it to continue the same email thread.
Returns an Email entity containing the message ID, thread token, recipient, subject, body, and optionally a reply or reply-timeout flag. Save the thread token if you want to continue or inspect the conversation later.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm send emails. Pass the returned LLM Tool entity into the tools argument of llm; the model can then call sendEmail when it has the recipient and message details.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that sendEmail call instead of returning a tool descriptor.
Returns an LLM Tool entity for sending email. The tool requires a recipient address and can optionally set subject, body, wait-for-reply, and thread token.
Paste the contents of your clipboard into Cell A1 of a worksheet
Fetch the full message history for an email thread. Use the thread token returned by sendEmail to review all messages in the conversation.
Thread token returned by sendEmail.
Returns an Email thread entity. In Excel, the card shows each message and exposes a hidden Messages table with number, sender, subject, date, and content; outside Excel it returns JSON.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm fetch an email thread by thread token. Pass this LLM Tool entity into the tools argument of llm when the model may need to inspect a conversation.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that getEmailThread call instead of returning a tool descriptor.
Returns an LLM Tool entity for retrieving email thread history by thread token.
Paste the contents of your clipboard into Cell A1 of a worksheet
Run Python code in the workbook's Python worker and return the value of the last expression as JSON. Use this for quick calculations, data reshaping, or analysis that is easier in Python than in formulas.
Python code to execute. The last statement should be an expression whose value can be serialized to JSON; convert NumPy and pandas values to plain Python lists, dicts, floats, ints, or strings before returning.
Returns the JSON-serialized value of the final Python expression, or a friendly Python error entity if execution fails. If the last statement is not an expression, the return value is JSON null.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm run Python code for calculations and data analysis. Pass the returned LLM Tool entity into the tools argument of llm when a model should be able to compute rather than only reason in text.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that runPython call instead of returning a tool descriptor.
Returns an LLM Tool entity for Python execution. The tool expects code whose final expression is JSON-serializable.
Paste the contents of your clipboard into Cell A1 of a worksheet
Package an Excel range as a named table that can be queried with DuckDB SQL. Use this once per source table, then pass the resulting SQL Data Table entities to sql or sqlTool.
Range containing the table. The first row must contain unique, nonblank column names, and column names cannot contain double quotes.
SQL table name to use in queries. It must start with a letter and contain only letters, numbers, and underscores.
Optional description of the table and any columns whose meaning is not obvious. This is especially helpful when the table is exposed to llm through sqlTool.
Returns a one-cell SQL Data Table entity. The entity stores the source range, table name, description, and inferred column types; pass these entities to sql for direct querying or to sqlTool so an LLM can query the data.
Paste the contents of your clipboard into Cell A1 of a worksheet
Run a DuckDB SQL query against one or more Excel ranges packaged by sqlDataTable. Use this when you want a normal spilled table result in Excel.
DuckDB SQL statement to run. Refer to each source range by the table_name you gave to sqlDataTable.
One or more SQL Data Table entities created by sqlDataTable.
Optional maximum serialized response size used when this query is exposed as an LLM tool. Defaults to 2000.
Returns a spilled table with column headers. Dates are converted to readable date strings and SQL NULL values appear as blanks when called from Excel.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm query selected Excel tables with DuckDB SQL. Use sqlDataTable to define each source table first, then pass those entities here, and pass the returned LLM Tool entity into llm as a tool.
One or more SQL Data Table entities created by sqlDataTable. Each table name must be unique. To run a pending SQL call manually, this argument may instead be its LLM Tool call entity.
Optional maximum serialized response size to tell the tool to allow. Defaults to 2000.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that sql call instead of returning a tool descriptor.
Returns an LLM Tool entity that includes the SQL schema, table descriptions, and fixed table references. Give the tool to llm so the model can write SQL and inspect workbook data without copying the full data into the prompt.
Paste the contents of your clipboard into Cell A1 of a worksheet
Search Google Maps Places with a plain-language query and return normalized place details. This function is staged because it calls an external service: after the formula shows Ready to run, select it and click Run staged cells in selection in the GenAI tab of the side bar.
Plain-language search text, for example Columbia University, pizza near Boston, or pharmacies near 10027.
Optional latitude for a circular location bias. Provide with restriction_longitude and restriction_radius_meters.
Optional longitude for a circular location bias. Provide with restriction_latitude and restriction_radius_meters.
Radius in meters for the location bias. Required if restriction_latitude and restriction_longitude are set; maximum 50000.
Optional place type filter. If set, only places with that exact Google place type are returned.
TRUE to return only places Google reports as currently open.
Returns a Google Maps places search entity with cost, result count, and a hidden results table. Results include place_id, display name, addresses, latitude, longitude, Google Maps URI, business status, phone, website, rating, and rating count.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm search Google Maps Places. Pass the returned LLM Tool entity into the tools argument of llm when the model may need to find businesses, addresses, or place IDs before taking another action.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that googleMapsPlacesSearch call instead of returning a tool descriptor.
Returns an LLM Tool entity for Google Maps place search. The tool returns normalized place records and billed cost metadata.
Paste the contents of your clipboard into Cell A1 of a worksheet
Compute route duration and distance between two Google place IDs. This function is staged because it calls an external service: after the formula shows Ready to run, select it and click Run staged cells in selection in the GenAI tab of the side bar.
Raw Google origin place ID, such as the place_id returned by googleMapsPlacesSearch.
Raw Google destination place ID, such as the place_id returned by googleMapsPlacesSearch.
Travel mode. Defaults to DRIVE.
TRUE to request traffic-aware routing. Only supported for DRIVE.
Optional RFC 3339 departure timestamp, for example 2026-05-12T15:01:23Z. Do not provide together with arrival_time.
Optional RFC 3339 arrival timestamp. Google only uses arrival time for TRANSIT routes. Do not provide together with departure_time.
Distance units. Defaults to IMPERIAL.
Returns a Google Maps route entity with duration, static_duration, distance, route description, warnings, traffic flag, and billed cost. Use place IDs from Places search rather than addresses for the most reliable routing.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm compute Google Maps route time and distance between place IDs. Pair it with the Places search tool when the model first needs to look up place IDs.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that googleMapsTravelTime call instead of returning a tool descriptor.
Returns an LLM Tool entity for route duration and distance. The tool requires origin and destination place IDs and supports mode, traffic, time, and units options.
Paste the contents of your clipboard into Cell A1 of a worksheet
Get current weather or an hourly forecast for a latitude/longitude from Google Maps Weather. This function is staged because it calls an external service: after the formula shows Ready to run, select it and click Run staged cells in selection in the GenAI tab of the side bar.
Latitude of the location, between -90 and 90.
Longitude of the location, between -180 and 180.
Units system. Defaults to IMPERIAL.
Optional New York date/time through which to return hourly forecast data, formatted YYYY-MM-DD,HH:MM. Leave blank for current conditions only.
Returns a Google Maps weather entity. Current weather exposes condition, temperature, feels_like, humidity, UV index, precipitation, wind, and cloud cover; forecasts expose a hidden forecast_hours table with those fields by hour.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm get current or forecast weather for a latitude/longitude. Pass the returned LLM Tool entity into llm when the model may need weather context.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that googleMapsWeather call instead of returning a tool descriptor.
Returns an LLM Tool entity for Google Maps weather. The tool requires latitude and longitude and can optionally request an hourly forecast through a New York time cutoff.
Paste the contents of your clipboard into Cell A1 of a worksheet
Fetch daily OHLCV stock prices for one or more equity tickers. This function is staged because it calls an external service: after the formula shows Ready to run, select it and click Run staged cells in selection in the GenAI tab of the side bar.
One or more stock ticker symbols. Select a row or column of tickers to request several at once; symbols are normalized to uppercase.
Start date as YYYY-MM-DD, or an Excel date cell.
End date as YYYY-MM-DD, or an Excel date cell. Must be after from and at least 24 hours ago.
Returns a spilled table with columns ticker, date, open, high, low, close, and volume. Multiple tickers are stacked in the same output table.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm fetch daily stock prices. Pass the returned LLM Tool entity into the tools argument of llm when the model may need historical OHLCV data.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that getStockPrices call instead of returning a tool descriptor.
Returns an LLM Tool entity for daily stock prices. The tool requires tickers, from date, and to date.
Paste the contents of your clipboard into Cell A1 of a worksheet
Search Duffel flight availability for a one-way, round-trip, or multi-city itinerary. This function is staged because it calls an external service: after the formula shows Ready to run, select it and click Run staged cells in selection in the GenAI tab of the side bar.
Cabin class for the search: economy, premium_economy, business, or first.
TRUE to allow one connection per leg; FALSE to search nonstop options only.
Origin IATA airport code for a simple one-way or round-trip search. Use with to_iata and outbound_date instead of legs.
Destination IATA airport code for a simple one-way or round-trip search. Use with from_iata and outbound_date instead of legs.
Outbound departure date formatted YYYY-MM-DD. Use with from_iata and to_iata instead of legs.
Optional return departure date formatted YYYY-MM-DD. Only used with from_iata, to_iata, and outbound_date.
Detailed flight legs for multi-city or constrained searches. Use a table with columns origin, destination, departure_date, and optional departure_time_from, departure_time_to, arrival_time_from, arrival_time_to. Use 3-letter IATA codes and YYYY-MM-DD dates.
Returns a Duffel flight search entity with Search ID and a hidden Results table. For multi-leg searches, choose a result's leg_id and pass the Search ID plus selected leg path to flightSearchNextLeg to retrieve the next leg options.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm search Duffel flight availability. Pass the returned LLM Tool entity into llm when the model may need to find flights or compare itineraries.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that flightSearch call instead of returning a tool descriptor.
Returns an LLM Tool entity for flight search. The tool supports either simple from/to/date fields or an ordered list of detailed legs with optional time windows.
Paste the contents of your clipboard into Cell A1 of a worksheet
Continue a Duffel multi-leg flight search after selecting a previous leg option. This function is staged because it calls an external service: after the formula shows Ready to run, select it and click Run staged cells in selection in the GenAI tab of the side bar.
Search ID returned by flightSearch.
Selected previous leg path from the result leg_id values, for example 1 or 1.2.5.
Returns a Duffel next-leg search entity with the same Search ID and a hidden Results table for the next leg. Continue passing the growing previous_legs path until the itinerary is complete.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm continue a Duffel flight search after selecting a previous leg. Use it together with the flight search tool for multi-leg itineraries.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that flightSearchNextLeg call instead of returning a tool descriptor.
Returns an LLM Tool entity for retrieving next-leg flight options by Search ID and previous leg path.
Paste the contents of your clipboard into Cell A1 of a worksheet
Get the workbook user's public IP address, approximate location, and time zone. Use this when you need coarse location context, not precise GPS coordinates.
Returns a two-column key/value table with fields from the IP lookup service, such as IP address, city, region or metro code, country, continent, and timezone when available.
Paste the contents of your clipboard into Cell A1 of a worksheet
Create an LLM tool that lets llm look up the workbook user's public IP address, approximate location, and time zone. Use this only for coarse context; it is not a precise geolocation tool.
Optional LLM Tool call entity from an LLM Output .tool_calls table. When provided, this function runs that ipInfo call instead of returning a tool descriptor.
Returns an LLM Tool entity for IP-based location lookup. The tool takes no arguments and returns approximate location metadata.
Paste the contents of your clipboard into Cell A1 of a worksheet
Generate random values from commonly used probability distributions for simulation models.
Generate a normally distributed simulation value.
Mean of the distribution.
Standard deviation; must be greater than zero.
A normally distributed random value.
Paste the contents of your clipboard into Cell A1 of a worksheet
Generate a binomially distributed simulation value.
Number of independent trials; must be a nonnegative integer.
Success probability for each trial, from zero to one.
A binomially distributed random integer.
Paste the contents of your clipboard into Cell A1 of a worksheet
Generate a Poisson-distributed simulation value.
Expected number of events; must be nonnegative.
A Poisson-distributed random integer.
Paste the contents of your clipboard into Cell A1 of a worksheet
Generate an exponentially distributed simulation value.
Event rate (lambda); must be greater than zero. The mean is 1 / rate.
An exponentially distributed random value.
Paste the contents of your clipboard into Cell A1 of a worksheet
Generate a uniformly distributed simulation value.
Smallest possible value.
Largest possible value; must exceed the minimum.
A uniformly distributed random value.
Paste the contents of your clipboard into Cell A1 of a worksheet
Generate a triangularly distributed simulation value.
Smallest possible value.
Mode of the distribution, between the minimum and maximum.
Largest possible value; must exceed the minimum.
A triangularly distributed random value.
Paste the contents of your clipboard into Cell A1 of a worksheet
Perform common worksheet transformations, set operations, counts, and positional lookups.
Find the unique values in the range provided, and the number of times each value occurs.
The values we're trying to summarize
Whether to return counts (COUNTS) or percentages (PERCENTAGES)
Whether text values with different capitalization should be counted separately. Defaults to TRUE.
Returns two columns with headings. The first contains the unique values in the input range, and the second contains the count or proportion for that value, sorted from largest to smallest.
Paste the contents of your clipboard into Cell A1 of a worksheet
Return the unique values from the first range that do not appear in the second range.
The range whose unique values should be returned.
The range whose values should be removed from the first set.
Returns a single-column spilled range containing the set difference, in first-appearance order.
Paste the contents of your clipboard into Cell A1 of a worksheet
Find the position of the nth largest value in a vector.
The numeric values to search.
Optional labels corresponding to the vector. When provided, returns the selected label instead of its position.
Which ranked value to return. Defaults to 1.
Returns the 1-indexed position of the requested value, or its corresponding label when labels are provided.
Paste the contents of your clipboard into Cell A1 of a worksheet
Find the position of the nth smallest value in a vector.
The numeric values to search.
Optional labels corresponding to the vector. When provided, returns the selected label instead of its position.
Which ranked value to return. Defaults to 1.
Returns the 1-indexed position of the requested value, or its corresponding label when labels are provided.
Paste the contents of your clipboard into Cell A1 of a worksheet