How do I give an AI agent access to our company documents in Google Drive?
You give an AI agent access to Google Drive by connecting a Google account to it through OAuth, which is Google's standard sign-in for letting an app act on your behalf. You sign in, Google shows you what the app is asking to do, and you approve it. From then on, the agent works with your Drive using that account's access. It can open whatever the account can open, including the shared drives the account belongs to, and it can't open anything the account can't.
Most AI tools offer this connection now. Gemini, built into Google Workspace, can summarize a file and answer questions about the documents in your Drive. ChatGPT and Claude both offer Google Drive connections that search and read your files while you chat. If you're building your own agent, Google's Drive API gives you two routes: an OAuth sign-in for one person's account, or a service account that a Workspace administrator lets act on behalf of users across your company.
All of these routes solve the access problem well. What they don't decide is which documents the agent should believe. A typical marketing Drive holds the current positioning doc next to last year's, a pricing one-pager that was never updated after the price change, and a folder of drafts nobody marked as drafts. An assistant that searches Drive at the moment you ask a question reads whatever matches your words, including the outdated file. Then the chat ends, and the next conversation starts from scratch.
So the job has two halves. The first is the connection. The second is turning your documents into reliable knowledge: finding the files that are current, pulling out the facts that should guide every piece of work, keeping a link to where each fact came from, and noticing when two documents disagree. A good result is an agent that already knows your positioning, customers, and plans when you ask it for a landing page, without anyone pasting in the brand guide again.
Kite does both halves. It connects to your Drive, reads the documents that matter, and records what they say in the knowledge base it reads before every task.
How to get started
Start by telling Kite where your documents are and what you'd like it to learn from them:
"Our positioning, brand guide, and customer research are in the Marketing folder in Google Drive. Read them and update what you know about us."
Kite is an AI marketer. It researches your business, builds a growth strategy, and ships the work that brings you new customers. You can work with Kite in your browser or in Slack, and the request works the same in either place.
You connect Google Drive once for your whole Kite team. Open the integrations page in the Kite web app, choose Google Drive, and sign in with the Google account you want Kite to use. If you ask Kite to read your Drive before it's connected, Kite replies with a link to connect it and picks the work back up once you have. Everyone on your team then benefits from the same connection.
Choose the account with some care, because Kite sees exactly what that account sees. If your marketing files sit in a shared drive, connect an account that belongs to it. If you'd rather Kite read only certain folders, connect an account that has access to just those folders.
By the time you ask, Kite has usually already researched your company from your website and its built-in sources. Your Drive fills in what that research can't see: the plans, decisions, and customer conversations that never made it onto a public page. Reading files and updating the knowledge base is routine work, so Kite does it and then tells you what it learned.
How Kite reads your Google Drive and learns from it
Which documents are worth reading?
Kite starts by finding the documents that describe your company as it is now. It searches your Drive and the shared drives your account belongs to by folder, file name, file type, and the words inside each file. It also reads each file's details, including its name, folder, description, and the date it last changed.
Those details are how Kite tells the current version from the old ones. When it finds two positioning docs, it compares when each was last changed and which folder each one lives in. A file in an "Archive" folder or one titled as a draft counts for less than the version your team keeps in its main folder. If you named a folder in your request, Kite works from that folder first and searches beyond it only when the job needs something the folder doesn't have.
Kite looks for the kinds of documents that should guide marketing work:
- Positioning and messaging docs
- Brand guides and voice guidelines
- Pricing and packaging one-pagers
- Customer interview notes and win-loss research
- Launch plans and quarterly goals
- Competitor research and battlecards
It skips files that won't change how it works, such as old event photos or a spreadsheet of expense receipts, even when it has access to them.
Reading each file
Kite reads each file in a form it can work with. A Google Doc comes through as text, and a Google Sheet comes through as a table of rows. Slides decks, PDFs, and other stored files open in their own formats. Google limits each exported Doc, Sheet, or Slides deck to 10MB, which is far more than a long text document needs.
As it reads, Kite separates facts that should shape every later task from detail that only matters for one job. "We sell to clinics with two to five locations" belongs in the knowledge base. The full transcript of a customer interview doesn't, although the objection that customer raised three times might. Kite records the lasting facts and keeps a link to the file, so it can go back to the full document whenever a task needs it.
Where does each fact go?
Kite files each fact on the page of your knowledge base where later work will look for it. The knowledge base is the set of written pages Kite keeps about your company, covering your positioning, products, pricing, customers, how you go to market, your competitors, your brand voice, and your visual identity. Every part of Kite reads the relevant pages before it starts work.
A new positioning statement updates your positioning page. A pricing one-pager updates your pricing. If your Drive holds a brand guide, Kite can adopt it as the team's standard in place of the version it pieced together from your website. Research about a competitor goes onto that competitor's own pages, so a rival's price or tagline never ends up in the description of your own company.
Every fact Kite records carries its source, which here is the Drive file it came from, and the date Kite last checked it. That lets Kite tell "the Q3 launch plan says" apart from "you told us in a conversation," and it tells Kite when a fact is old enough to check again before relying on it.
What happens when two documents disagree?
Kite settles conflicts by trusting the most authoritative source and asking about the rest. Anything someone on your team told Kite directly outranks what a document says, so a file in Drive never quietly overwrites a decision you made in conversation. If a document contradicts something you've told Kite, Kite leaves your version in place and points out the difference so you can decide.
When two documents disagree and neither one is clearly newer or more official, Kite doesn't average them into a vague middle. It records the conflict as an open question and asks you about it. A typical case is a sales deck that still lists last year's plans while the pricing doc has the new ones. Kite tells you which two files disagree and what each one says, and you answer in one reply.
Recording where your documents live
Kite also notes which folders hold which kinds of documents in its record of where your team's information lives. The next time a task needs your latest customer research or the current launch plan, Kite goes straight to the right folder instead of asking you where to look.
What Kite reports back
When it finishes, Kite posts a summary in the conversation where you asked. The summary covers:
- The files it read, each with a link
- What it added or changed in the knowledge base
- The files it skipped and why, such as an older version or an unrelated spreadsheet
- Any conflicts between documents that need your answer
You can check what Kite learned at any time by asking it, for example, "What do you know about our pricing?" It answers from the knowledge base and tells you which file each answer came from.
Keeping up as your team adds new files
Kite can check your Drive on a schedule and read only what's new since its last look. Ask it to look at your Marketing folder every Monday, and it finds the files added or changed since the previous check, reads them, and updates the knowledge base. A folder of sales call notes works especially well this way, because the phrases customers keep repeating end up in the next landing page Kite writes.
Each scheduled check runs on its own. If your team uses Slack, the summary goes to the channel you choose. Without Slack, Kite emails the summary to the person who set up the check, and you can also keep the results in the Kite web app. Kite can save its own finished work back into Drive too, so a campaign brief or a report lands in the folder where your team keeps everything else.
What the finished work contains
When Kite finishes, your knowledge base reflects what your own documents say, and you have a clear record of where each fact came from.
Updated knowledge base pages
Your positioning, products, pricing, customers, competitors, brand voice, and plans are drawn from the Drive files you pointed Kite to, with each fact linked to its source file and dated.
Your brand guide as the standard
When your Drive holds a brand guide, Kite works from it for every page, email, and post it writes.
A map of your Drive
Kite's record of where your information lives notes which folders hold your research, plans, and brand files, so later tasks go to the right place.
Open questions
Each conflict between documents is listed with the files involved, so you can settle it in one reply.
The summary in your conversation
It lists what Kite read, what it changed, and what it skipped and why.
A recurring check, if you asked for one
Each run reads new and changed files and posts its own summary.
Common questions
Can an AI agent see everything in my Google Drive?
An AI agent can see everything the connected Google account can open, and nothing beyond it. Kite works with the full access of the account you connect, so that account sets the boundary. If you want Kite to read only your marketing files, connect a Google account that has access to those folders and not the rest of your company's Drive.
What kinds of files can Kite read from Google Drive?
Kite reads Google Docs, Google Sheets, Google Slides, PDFs, and other files stored in Drive, including images. Docs arrive as text and Sheets as tables, which makes them the easiest to learn from. A scanned PDF or a deck that's mostly images still opens, but a document written as text gives Kite more to work with.
Do I need to connect Google Drive for Kite to read a document?
No, you can share a single document with Kite without connecting Drive. Upload a PDF in the Kite web app or share the file in Slack, and Kite reads it there. Connect Drive when you want Kite to find documents on its own, read a whole folder, and keep up as your team adds new files.
What happens if someone updates a document after Kite reads it?
Kite picks up the change the next time it reads the file. That happens when a task depends on the document, when you ask Kite to read it again, or on a scheduled check of the folder. Because each fact in the knowledge base records the file it came from and when Kite last checked it, Kite knows which facts to refresh when a file changes.