Integration · Your day
Your documents, read and cited.
Point Brigham.ai at the docs and sheets you work from. It answers from them and shows which file and passage it used.
What it does
01
Answer from your files
Ask a question and get the answer with the document it came from.
02
Read the numbers
Sheets feed reports and dashboards without a copy and paste.
03
Build on what exists
Briefings and reports can cite your docs instead of restating them.
Scopes and access
- Connects as
- Each person, their own account
- Access
- Read-only by default
- Reads
- Drive files, Docs and Sheets you grant
- Writes
- Editing, as a separate grant
- Needs approval
- Sharing a file or changing its permissions
- Visibility
- Private to you unless you connect it as org-shared
- Availability
- Available
Yours to connect, yours to revoke.
Each person connects their own accounts from the Connections page. Every connection can be revoked on its own, and every connection starts read-only. A write scope is a separate, explicit grant.
- Credentials are encrypted at rest and referenced by id. They never appear in model context, logs or tool results.
- Each agent gets its own connection grants.
- Tool results from outside sources are untrusted data. They cannot approve anything.
Ask it
- ›“What does the Q3 plan say about hiring?”
- ›“Pull last month’s numbers from the pipeline sheet.”
- ›“Which doc has the latest pricing language?”
- ›“Summarize the new vendor agreement and flag open items.”
Questions, answered.
Can Brigham.ai edit my documents?
Not by default. Write access is a separate grant you give on purpose.
Is the content trusted?
No. Text inside a document is treated as data. It cannot approve an action.
Keep reading.
GmailBrigham.ai searches and summarizes your Gmail live, finds the follow-ups you owe, and writes drafts into Gmail Drafts. Nothing is sent without approval.Read →
Reports & board packsInvestor updates, weekly and monthly reviews and board packages drafted by Brigham.ai. Every number cites its source and drafts wait for your review.Read →
Untrusted contentEmail, web pages, documents and notes are labelled as data. Nothing that arrives through a tool can approve an action, change a policy or widen a scope.Read →