Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Google Docs API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Google Docs API.
Create a new Google Docs document with a starting title
Retrieve the full structural representation of a document
Insert and replace text at specific document indices
Apply paragraph and character styles to ranges (headings, bold, links)
GET STARTED
For Agents
Create Google Docs and apply rich content edits - text, styles, images, tables - via batched structural updates.
Use for: I need to create a Google Doc from a templated brief, Insert a heading and body text into an existing Google Doc, Replace placeholder tokens like {{NAME}} in a Google Doc, Get the full structure of a Google Doc to extract content
Not supported: Does not handle file sharing, folder placement, or commenting - use for content authoring inside a Google Doc only; use Drive for file management.
The Google Docs API lets applications read and write Google Docs documents programmatically. Three endpoints - create, get, and batchUpdate - cover document creation, structural retrieval, and a rich batchUpdate language for inserting text, applying styles, embedding images, managing tables, and moving content. Used for templated document generation (contracts, reports, briefs), AI-assisted authoring, and content pipelines that produce shareable Docs at scale.
Insert images, tables, and named ranges via batchUpdate
Move and merge content while preserving styles
Patterns agents use Google Docs API for, with concrete tasks.
★ Templated Document Generation
Operations teams generate contracts, reports, and briefs by creating a fresh Google Doc, then sending a single batchUpdate with insertText and replaceAllText requests to populate the template. The whole document - including styles, tables, and images - is built in one round-trip, so a 20-page customer report renders in seconds.
Create a Google Doc titled 'Q2 Customer Report - Acme Corp', then send a batchUpdate with insertText for the title heading, three section bodies, and an inline image at the top.
Token Substitution in Existing Docs
Marketing and legal teams maintain master Docs with placeholders like {{ClientName}} or {{Date}}. The replaceAllText request in batchUpdate swaps every occurrence in one call without touching surrounding styles. The same Doc can be cloned (via Drive) and personalised in a few hundred milliseconds per recipient.
Send a batchUpdate to document 1abcXYZ with replaceAllText requests mapping {{ClientName}} to 'Acme Corp' and {{Date}} to '2026-06-10'.
Programmatic Style Application
Pair documents.get with batchUpdate to read the structure, identify ranges (paragraphs, runs, tables), and apply consistent styling - heading levels, font choices, bold/italic, hyperlinks. Agencies use this to enforce brand styles across hundreds of imported Docs in one pipeline run.
Get document 1abcXYZ, find every paragraph whose text starts with 'Section', and send a batchUpdate that applies HEADING_2 paragraph style to those ranges.
Agent-Authored Briefs and Memos
Through Jentic, an AI agent can take a structured brief (a JSON payload of headings, paragraphs, and bullets) and emit a finished Google Doc by calling documents.create followed by a single batchUpdate. Credentials are scoped per agent run by your Jentic One instance - Drive sharing happens separately via the Drive API.
Use Jentic to search 'create a Google Doc and add content', load the schemas for documents.create and documents.batchUpdate, then build a Doc with a title, three headings, and three body paragraphs from a JSON brief.
3 endpoints — the google docs api lets applications read and write google docs documents programmatically.
METHOD
PATH
DESCRIPTION
/v1/documents
Create a new Google Doc
/v1/documents/{documentId}
Get the full structure of a Google Doc
/v1/documents/{documentId}:batchUpdate
Apply a batched set of structural edits
/v1/documents
Create a new Google Doc
/v1/documents/{documentId}
Get the full structure of a Google Doc
/v1/documents/{documentId}:batchUpdate
Apply a batched set of structural edits
Three things that make agents converge on Jentic-routed access.
Credential isolation
Your Google OAuth credential for Google Docs is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'insert text into a Google Doc' or 'read a document's content', and Jentic returns the matching Google Docs operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Time to first call
Alternatives and complements available in the Jentic catalogue.
Specific to using Google Docs API through Jentic.
What authentication does the Google Docs API use?
OAuth 2.0 with the documents or documents.readonly scope (and drive scopes for sharing). Through Jentic, OAuth tokens are scoped per agent run and stored encrypted in your Jentic One instance, so service-account JSON keys never enter the agent runtime.
Can I insert text and images into an existing Doc?
Yes. Send a batchUpdate to /v1/documents/{documentId}:batchUpdate with a list of requests including insertText, insertInlineImage, insertTable, and updateParagraphStyle. The whole edit applies in one transaction.
What are the rate limits for the Google Docs API?
Google Docs enforces a default of 300 read requests and 60 write requests per minute per user, plus daily project quotas. Heavy batchUpdate calls count once toward write quota even if they include many sub-requests.
How do I create a new Google Doc through Jentic?
Search 'create a Google Doc', load the schema for /v1/documents (POST), then execute it with a title in the request body. Jentic returns the new document ID, which you then use in subsequent batchUpdate calls.
Does the Google Docs API let me share or move documents?
No. Sharing, folder placement, and ownership transfers are managed through the Google Drive API, not the Docs API. Use Drive's permissions and files endpoints for those actions.
Is the Google Docs API free?
Yes. The Docs API has no per-call charge for standard usage within quota - you pay only if you have a Google Workspace subscription for the underlying account, and there is no separate API metering.