ask_gcai
ChatGPTAsk GC AI a legal question or give it a task. Optionally ground it in uploaded files (file_ids), playbooks (playbook_ids), skills (skill_ids), or a Contract Intelligence vault (vault_id). Returns a job envelope, not a final answer: while status is pending or running, keep polling ask_gcai_status with the returned job_id until status is succeeded (then result holds the answer). Pass chat_id to continue a prior conversation, sending only the new message (conversation state is kept server-side).
ask_gcai_save_chat
ChatGPTSave an ask_gcai chat into GC AI history and return a shareable deep link. API chats stay out of history until saved. Pass project_id to also file the chat into a project you can edit. Idempotent: saving a chat that is already saved (and already in that project) returns the same link with no side effects.
ask_gcai_status
ChatGPTPoll a chat completion started by ask_gcai, using the job_id it returned. While status is running or pending, poll again; when succeeded, result holds the answer.
attach_to_project
ChatGPTLink existing files to a project. Membership is a separate edge, not a field on the project. Idempotent: re-linking a file is a no-op. Files you cannot access are reported in not_found and skipped; the rest are linked.
create_playbook
ChatGPTCreate a playbook — a reusable set of review checks. You own it and it is private to you. Pass checks to author them inline, or add them later with update_playbook. Returns the playbook and its checks.
create_project
ChatGPTCreate a project to group files, folders, and chats around a single matter. You are recorded as the creator with admin access. Add files with attach_to_project; membership is managed separately, not on this call.
create_skill
ChatGPTCreate a skill — a reusable instruction the model applies on demand. You own it and it defaults to private. Attach reference files with file_ids (upload them first). Returns the created skill.
create_vault
ChatGPTCreate a Contract Intelligence vault. The caller becomes its owner and the vault starts private to them, so nobody else sees it until they are added in the app. The vault is ready for documents right away: add them with upload_file using the returned id as vault_id, then add the columns you want extracted with create_vault_column. Creating a vault needs a permission an organization admin grants.
create_vault_column
ChatGPTAdd a column to a vault, so GC AI extracts one more thing from its documents. Adding a column does NOT read the documents already in the vault: it starts empty for all of them and fills in for documents added afterwards. Backfilling the existing ones is a separate action someone takes in the app, so say so rather than waiting for values to appear. A vault holds at most 500 columns.
detach_from_project
ChatGPTUnlink files from a project. Membership is a separate edge, not a field on the project. Idempotent at the membership level: detaching a file that is not linked leaves membership unchanged and is safe to retry. This removes the project link only; the file itself is not deleted.
finish_file_upload
ChatGPTFinish an upload started with start_file_upload, after you have PUT the file bytes to its upload_url. Verifies the uploaded bytes, stores and processes the file (text extraction + embeddings), and returns the file record. Poll readiness with get_files({ id }) until status is "ready" (then use the file) or "failed" (then extraction_error explains why).
get_files
ChatGPTList files. Pass id to fetch one file (and poll its upload status), q to search files you can access (optionally narrowed by scope), or project_id to list a project's files (add q to search within them). Always returns a files array — empty when nothing matches. Calling with none of id, q, or project_id is an error: there is no full file listing, only lookup, search, and per-project listing.
get_playbooks
ChatGPTList or fetch playbooks. Pass id to fetch one playbook including its full guide text. Otherwise returns a page of playbooks you can access (those you created, org-visible, shared with you, and official ones); narrow with q and page with cursor/limit. Always returns a playbooks array (empty when nothing matches) and a next_cursor (null on the last page).
get_projects
ChatGPTList or fetch projects. Pass id to fetch one project. Otherwise returns a page of projects you can access (those you created, open projects, and ones shared with you); narrow with q and page with cursor/limit. Always returns a projects array (empty when nothing matches) and a next_cursor (null on the last page).
get_skills
ChatGPTList or fetch skills. Pass id to fetch one skill including its full content. Otherwise returns a page of skills you can access (those you created, org-visible, shared with you, and official ones) as summaries without content; narrow with q and page with cursor/limit. Always returns a skills array (empty when nothing matches) and a next_cursor (null on the last page).
get_vault_columns
ChatGPTList the columns of a vault: what GC AI extracts from every document in it. Read this before get_vault_documents so you know which field_key to filter and sort on and what each value means. kind says who owns the column: built_in and system columns come from GC AI and cannot be changed, and custom columns belong to this vault. Only a column with editable: true can be changed with update_vault_column.
get_vault_documents
ChatGPTRead a vault's table: one row per document, with the value GC AI extracted for every column. This is the tool for questions the table can answer directly, such as which contracts expire this quarter, which name a counterparty, or which are missing a value. Narrow with filters and sort rather than paging everything. values is keyed by column field_key; read the keys, labels, and types from get_vault_columns first. A value is a string, and structured columns carry JSON in it: a currency holds {"amount","currency"}, a date holds YYYY-MM-DD, a multi-select holds a JSON array. null means the scan found no value. A document appears here once its first scan writes values, a few minutes after upload, so a row missing right after upload_file is not lost. To answer from the text inside the documents rather than the extracted columns, use ask_gcai with this vault instead.
get_vaults
ChatGPTList or fetch Contract Intelligence vaults. A vault holds a set of contracts that GC AI has read, with the extracted fields the team tracks. Pass id to fetch one vault. Otherwise returns a page of the vaults you can access; narrow with q and page with cursor/limit. Always returns a vaults array (empty when nothing matches) and a next_cursor (null on the last page). Use a returned id as vault_id when adding a document with upload_file or start_file_upload, or to ground ask_gcai in that vault's documents. Archived vaults are not listed. document_count is the number of documents that have finished scanning and can lag a fresh upload; confirm an upload with get_files({ id }), not with this count.
run_playbook
ChatGPTRun a playbook (by id) against uploaded files (file_ids) and get structured check results. Files must be uploaded and ready first; the playbook must be completed. Pass check_ids to run a subset of checks, or omit to run all. Returns a job envelope, not final results: while status is pending or running, keep polling run_playbook_status with the returned job_id until status is succeeded (then result holds the check results).
run_playbook_status
ChatGPTPoll a playbook run started by run_playbook, using the job_id it returned. While status is running or pending, poll again; when succeeded, result holds the check results.
start_file_upload
ChatGPTStart uploading a file that only exists in your local/sandbox filesystem (use this when no host-attached file reference is available, e.g. on Claude). Returns a short-lived signed upload_url: PUT the file bytes straight to it from your sandbox, for example curl -X PUT --upload-file <path> "<upload_url>". Then call finish_file_upload with the returned file_id to register and process the file. Target with project_id, vault_id, or scope (mutually exclusive, default "my-files"). If the host already populates a file reference, prefer upload_file instead.
update_playbook
ChatGPTUpdate a playbook you can write to. Only the fields you pass change. Pass checks to replace the whole check set (read it first, edit, send it back); omit checks to leave them. Returns the playbook and its checks.
update_project
ChatGPTUpdate a project you can write to. Only the fields you pass change; omit a field to leave it, or pass null to description/custom_instructions to clear it. Membership is managed with the attach/detach tools, not here.
update_skill
ChatGPTUpdate a skill you can write to. Only the fields you pass change; omit a field to leave it. file_ids replaces the whole attachment set. Visibility is not editable here — manage skill sharing in the GC AI app.
update_vault
ChatGPTChange a vault's name, description, who can see it, or whether it is archived. Send only what should change. Archiving hides the vault and stops changes to it without deleting anything, and restoring brings it back with its documents intact. Only a vault owner can do any of this. Deleting a vault permanently is not available here; that is done in the app or on the REST API.
update_vault_column
ChatGPTChange a vault column's heading, extraction instructions, type, or options. Send only what should change. Only a custom column can be changed; GC AI owns the built-in and system columns and refuses. Changing the type of an AI column re-reads the documents that already have a value for it, which counts against the daily re-analysis limit, so the result says what happened to that re-scan.
update_vault_document_cell
ChatGPTCorrect one extracted value on one document, the way a person would fix a cell in the vault table. Pass value to set it, or revert: true to undo an earlier hand edit and put the AI value back. An edit wins over any scan that lands afterwards, so there is no need to wait for a scan to finish. A column GC AI manages, and a value outside a select column's options, are both refused.
upload_file
ChatGPTUpload a file the user has attached into GC AI. To upload, just call this tool: the host populates the file argument automatically. Do not read or pass a local/sandbox path (e.g. /mnt/data/...) and do not construct file.download_url yourself. The bytes are fetched, stored, and processed (text extraction + embeddings) in place. Poll readiness with get_files({ id }) until status is "ready" (then use the file) or "failed" (then extraction_error explains why). Target the upload with project_id (into a project), vault_id (as a document in a Contract Intelligence vault), or scope ("my-files" / "organization"); the three are mutually exclusive and default to "my-files".
ask_gcai
Claudeask_gcai_save_chat
Claudeask_gcai_status
Claudeattach_to_project
Claudecreate_playbook
Claudecreate_project
Claudecreate_skill
Claudecreate_vault
Claudecreate_vault_column
Claudedetach_from_project
Claudefinish_file_upload
Claudeget_files
Claudeget_playbooks
Claudeget_projects
Claudeget_skills
Claudeget_vault_columns
Claudeget_vault_documents
Claudeget_vaults
Clauderun_playbook
Clauderun_playbook_status
Claudestart_file_upload
Claudeupdate_playbook
Claudeupdate_project
Claudeupdate_skill
Claudeupdate_vault
Claudeupdate_vault_column
Claudeupdate_vault_document_cell
Claudeupload_file
Claude