Secure AI Agent · Executive Assistant
AI applied to the executive routine
A specialist configured to protect the calendar under your standing rules, deliver the brief before each meeting, triage the inbox, and chase decisions until they are done.
Companies that trust UPX
Capabilities
What the Executive Assistant can do
Main areas of work for the Executive Assistant AI Agent in your routine.
Calendar protection
Applies the executive's standing rules to incoming meeting requests.
Meeting brief
Delivers one page with context, attendees, and what needs to be decided.
Inbox triage
Separates what needs the executive's reply and prepares the draft.
Travel organization
Builds the itinerary with times, transfers, and chained commitments.
Decision follow-through
Tracks what was decided and flags what has not moved.
Day preparation
Consolidates the next day with what needs attention in advance.
Skills
Capabilities that compose the specialist
Skills add specific capabilities to the Secure AI Agent according to the processes it needs to execute.
- Calendar rule enforcement
- Checks each request against the executive's standing rules.
- Context synthesis
- Gathers history and documents into a one-page brief.
- Open-item tracking
- Keeps the list of what was decided and not yet executed.
From calendar to decision, with the executive in control
Connect calendar and inbox, define the standing rules, and let the preparation happen within your limits.
- Connect calendar and inbox
- The agent works where the routine already happens.Connect the calendar, the inbox, the team channels, and the document base so the Secure AI Agent has access only to what it needs to prepare the day.
- Define the standing rules
- The agent applies your criteria, not its own.Record what protects the calendar: untouchable blocks, meeting types that require an agenda, daily hour limits. The agent then applies those rules to every new request.
- The agent prepares. You decide.
- Nothing goes out in your name without review.The agent triages, summarizes, and follows up within the defined permissions. Sending email in your name, confirming external commitments, and approving expenses still require your approval.
01
02
03
Integrations
Connected to the tools in your routine
The Executive Assistant can query your calendar and run tasks in the systems you already use.
Flow
What goes in, what the agent does, and what comes out
From scattered requests to a prepared day, following the executive's standing rules.
Inputs
- Meeting requestsICS
- InboxAPI
- Standing rulesDOC
Processing
Secure AI Agent
Processing the task
- Read
- Triage
- Summarizerunning
- Follow up
Output
Completed
Day prepared
- Calendar aligned to the rules
- One-page brief per meeting
- Open decisions listed
Control
You define how far the Agent can act
Different actions can operate with different autonomy levels, always within your rules.
- 1
Query
Reads calendar and inbox and answers with the reference.
- 2
Prepare
Builds the brief and the draft reply.
- 3
Request review
Waits for the executive's decision.
- 4
Execute
Performs the action within the defined limits.
Levels are configured per type of action. Sending email in the executive's name, confirming external commitments, and approving travel expenses always stay under human approval.
Get started
Put a Secure AI Agent to work.
Start on the platform or choose the plan that fits the pace of your operation.
Security that can be verified.
Certifications and attestations
UPX maintains SOC 2 Type II and ISO 27001, with independent audit over its information security controls.
Privacy and regulation
- LGPD
- Operations follow Brazil's Law 13.709/2018. In AI Agent contracts, UPX acts as data processor; the legal basis remains with your company.
- Zero Data Retention
- A product policy, not a certification: all market AI models used by the Agents have ZDR under contract, and processed content is not retained after execution.
- Retention and deletion
- The retention policy is defined by contract. Once the contract ends, data is deleted within the agreed period.
Frequently asked questions
Common questions about the Executive Assistant
What executives and assistants usually ask before putting an agent into the routine.
Does the agent decline meetings on its own?
It applies the standing rules the executive defined — protected blocks, agenda requirements, hour limits. Anything outside the rule is flagged for a decision, not declined on its own judgment.Does it reply to email in the executive's name?
Not by default. It triages the inbox, separates what needs a reply, and prepares the draft. Sending stays with whoever signs, unless a higher autonomy level is configured for specific cases.What goes into the meeting brief?
Subject context, attendees, relevant history, and what needs to be decided — in one page. The content comes from the documents and conversations the agent has authorized access to.How does decision follow-through work?
The agent keeps the list of what was decided and tracks what has not moved, flagging it at the agreed cadence. It notifies; escalating to others stays the executive's decision.Is inbox content used to train models?
No. Content processed by Secure AI Agents is not used to train UPX models or third-party models.Can we audit what the agent did?
Yes. Every action is logged: what was queried, what was proposed, when, in which system, and under which permission. The history stays available for review and auditing.How long does it take to go live?
It depends on the systems involved. The starting point is connecting calendar and inbox and recording the standing rules, then expanding the scope as confidence in the triage builds.
Custom agents
We build and manage the agent for your executive office
From calendar protection to decision follow-through: we build the agent that prepares the executive's day.