# Gigasheet AI integration on Definable

> Gigasheet is a big data automation platform that offers a spreadsheet-like interface for analyzing and managing large datasets, enabling users to automate tasks, integrate with various data sources, and streamline data workflows.

## What this connects

Gigasheet is a big data automation platform that offers a spreadsheet-like interface for analyzing and managing large datasets, enabling users to automate tasks, integrate with various data sources, and streamline data workflows.

Vendor: https://gigasheet.com/api

## Tools available

**150** tools available. First 12:

- `GIGASHEET_APPEND_DATASET` — Append Rows to Dataset — Appends rows to an existing Gigasheet dataset using column letters as keys. Use when you need to add new data rows to a sheet by specifying values for each column position (A, B, C, etc.).
- `GIGASHEET_APPEND_DATASET_FROM_SHEET` — Append Sheet from Another Sheet — Tool to append data from a source sheet to a target sheet by matching column names. Use when you need to combine data from two existing sheets based on column name matching rather than column IDs. This action matches columns from the source sheet to the target sheet based on column names, with options for case-insensitive matching and trimming whitespace. Unmatched columns can optionally be added as new columns to the target sheet.
- `GIGASHEET_APPLY_USER_DEFINED_HTTP_ENRICHMENT` — Apply HTTP Enrichment — Tool to apply generic HTTP enrichment to a Gigasheet dataset. Use when you need to enrich dataset rows by calling external APIs and adding the response data as new columns. This action creates an enrichment job that calls a specified HTTP endpoint for each row (or batch of rows) in your dataset, extracts data from the API responses using JSON paths, and creates new columns with the enriched data. The operation is asynchronous and returns a job handle for monitoring progress. Common use cases: - Enrich customer records by calling a CRM API - Validate email addresses using a validation service - Lookup product details from an external catalog - Geocode addresses using a mapping API - Fetch social media profiles for contact enrichment
- `GIGASHEET_CALCULATE_ENRICH_EXPECTED_CREDITS` — Calculate Enrich Expected Credits — Calculate expected credits for a user-defined HTTP enrichment operation. Use this before initiating an enrichment to estimate costs based on the number of rows and columns that will be processed. This tool helps you: - Estimate credit costs before running an enrichment - Understand resource requirements for filtered enrichments - Plan budget for large-scale enrichment operations
- `GIGASHEET_CANCEL_ENRICH_USER_DEFINED_HTTP_TASK` — Cancel HTTP Enrichment Task — Tool to cancel a running enrichment task. Use when you need to stop an in-progress HTTP enrichment job that was previously initiated. This action attempts to cancel an enrichment task identified by its task handle. Cancellation is only possible for tasks that are still in progress (not yet completed or already failed). The task handle is returned when you start an enrichment job using the apply enrichment endpoint.
- `GIGASHEET_CHECK_CONNECTORS_SOURCES_CONNECTORNAME` — Check Connector Source Availability — Tool to check if a source of the given type is available. Use this to verify whether a specific connector integration (e.g., Snowflake, Salesforce) is configured and available for the authenticated user. This updates corresponding connection statuses.
- `GIGASHEET_COMBINE_FILES` — Combine Files — Tool to combine multiple files into a new file. Use when you need to merge several files where column names and types match. Optionally add source filename tracking or append rows to the first file in-place.
- `GIGASHEET_COPY_FILE` — Copy File — Tool to copy a file in Gigasheet. Use when you need to duplicate an existing file/sheet into your library with an optional new name and destination folder.
- `GIGASHEET_COUNT_DATASET_DEDUPLICATE_ROWS` — Count Dataset Deduplication Results — Tool to count how many duplicates will be removed and how many rows remain when deduplicating. Use when you need to preview the impact of a deduplication operation before executing it, or to understand the number of duplicate rows in a dataset based on specific column combinations.
- `GIGASHEET_COUNT_DATASET_GROUPS` — Count Dataset Groups — Tool to count the number of groups matching certain criteria in a Gigasheet dataset. Use when you need to determine how many distinct groups exist based on specified row grouping columns and optional filters. This action is useful for understanding data distribution and cardinality before performing more expensive operations like full group aggregations. It supports advanced features like pivot mode, filtering, and sorting configurations.
- `GIGASHEET_COUNT_DATASET_ROWS` — Count Dataset Rows — Counts rows in a Gigasheet dataset matching specified filter criteria. Returns the number of rows matching the provided filters, groupings, and other parameters. For basic row counting, only the handle and optionally filterModel need to be specified. Advanced features like pivot mode, grouping, and aggregations are available for complex counting scenarios. Common use cases: - Count all rows in a dataset - Count rows matching specific filter conditions - Count grouped rows in pivot tables - Validate filter results before exporting data For detailed information on constructing filter models, refer to the Gigasheet Filter Model Detail Guide at https://gigasheet.readme.io/reference/post_dataset-handle-count-rows
- `GIGASHEET_COUNT_DATASETS_ACTIVITY_COUNT` — Count Dataset Activities — Tool to get total activity count on a given Gigasheet dataset. Use when you need to determine how many activities (creates, updates, deletes) have been performed on a dataset. This action counts activities matching the specified criteria such as time range, users, action types, and categories. Non-blank criteria are AND-ed together, while multi-value fields (Actions, Categories, Users) are OR-ed. Returns the total count of matching activities.

## Auth

Auth schemes: `API_KEY`.

## How agents use Gigasheet

Inside a Definable workflow, Gigasheet is one of the tools the **Distributor specialist** can call. Example coordination patterns:

- **Researcher → Gigasheet** — the Researcher (GPT-5.5) pulls context from Gigasheet (records, threads, documents), synthesises findings, and briefs the rest of the team.
- **Writer → Distributor → Gigasheet** — the Writer (Claude Opus 4.7) drafts copy in brand voice, the Verifier passes it, then the Distributor writes the result into Gigasheet (create record, post message, draft email).
- **Designer / Engineer → Distributor → Gigasheet** — the Designer ships an asset or the Engineer ships a code change, the Distributor delivers it via Gigasheet (attach file, open PR comment, post status).

The Verifier checks every Gigasheet call. On rate limit, schema drift, or auth refresh it self-heals and retries — the workflow completes without manual intervention.

## Categories

- spreadsheets — https://definable.ai/apps/category/spreadsheets/
- analytics — https://definable.ai/apps/category/analytics/

## Related

- HTML page: https://definable.ai/apps/gigasheet/
- Same category (spreadsheets): https://definable.ai/apps/category/spreadsheets/
- All integrations: https://definable.ai/apps/
- Workflow (multi-agent loop): https://definable.ai/workflow/
- Apps llms.txt index: https://definable.ai/llms-apps.txt