Secure AI Agent · General Assistant

Your company's first agent

A versatile assistant that organizes email, calendar, documents, and administrative routines, learns how your operation works, and gradually takes on recurring work — always proposing before acting.

Companies that trust UPX

  • Bradesco
  • Nubank
  • BTG Pactual
  • Totvs
  • Ascenty
  • Live!
  • G4 Educação
  • EVEO

Capabilities

What the General Assistant can do

Main areas of work for the General Assistant AI Agent in your company's routine.

Inbox triage

Separates what needs a decision from noise and drafts the reply.

Calendar and meetings

Organizes commitments, prepares agendas, and records what was agreed.

Documents and files

Finds, summarizes, and organizes what is scattered across folders.

Follow-ups that stick

Chases a pending item with a third party until it closes.

Recurring routines

Runs what repeats every week in the same format.

Quick lookups

Answers with the figure or the clause and shows where it came from.

Skills

Capabilities that compose the specialist

Skills add specific capabilities to the Secure AI Agent according to the processes it needs to execute.

Email triage
Sorts by urgency and drafts the reply for review.
Meeting preparation
Builds the agenda with history, pending items, and open decisions.
Document search
Locates the passage and answers with the reference.
How it works

From first access to an owned routine

Connect your sources, define what the agent can do, and expand the scope as the routine proves itself.

01

Connect what the company already uses
Email, calendar, and folders, with no migration.Connect the inbox, the calendar, and the file base so the Secure AI Agent has access only to what it needs to support the administrative routine.

02

Ask for the work
Talk to the agent in natural language.Ask for the day's triage, a meeting agenda, or a contract summary through the available channels. The agent understands the context, applies the configured skills, and follows the company's rules.

03

The agent proposes. You approve.
Autonomy grows with track record.At first everything goes through review. As the routine proves reliable, you release the actions that no longer need approval — and the sensitive ones keep requiring it.

Integrations

Connected to the tools where the day happens

The General Assistant can query your sources and run tasks in the systems your team already uses.

  • Gmail
  • Google Calendar
  • Google Drive
  • Slack
  • Notion

Flow

What goes in, what the agent does, and what comes out

From a raw inbox to an organized day, following your company's rules and permissions.

Inputs

  • InboxEMAIL
  • Week's calendarICS
  • Document folderPDF

Processing

Secure AI Agent

Processing the task

  • Read
  • Classify
  • Draftrunning
  • Prepare
Skill appliedPermission verified

Output

Completed

Work prepared

  • Inbox triaged by urgency
  • Drafts ready for review
  • Meeting agenda assembled

Control

You define how far the Agent can act

Different actions can operate with different autonomy levels, and each level changes whenever you want.

  1. 1

    Query

    Reads email, calendar, and files and answers with the reference.

  2. 2

    Prepare

    Drafts the reply and assembles the agenda for review.

  3. 3

    Request review

    Waits for approval before sending or scheduling.

  4. 4

    Execute

    Performs the action within the defined limits.

Levels are configured per type of action. Sending communication on the company's behalf, approving expenses, and signing documents always stay with an accountable person.

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 and compliance

Security that can be verified.

Certifications and attestations

  • SOC 2 Type II
  • ISO 27001

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: with compatible providers and configurations, 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 General Assistant

What companies usually ask before putting their first agent to work.

  • Where should we start?

    With the routine that consumes the most time and requires the least judgment: email triage, calendar organization, and document search. These show results in the first week and carry low risk, because the agent prepares and you review.
  • Does it send email on my behalf?

    Only if you release that action. By default the agent drafts and leaves it ready for review. Sending communication on the company's behalf is a sensitive action and stays under approval until you decide otherwise.
  • How is it different from a specialist agent?

    The General Assistant is broad and works as an entry point: it covers the administrative routine of any area. Specialists bring the vocabulary, rules, and controls of a function or an industry. Most companies start here and specialize later.
  • Does it learn how our company works?

    Yes, within what you connect. The agent uses your documents, history, and routines as context to answer in your house style. That context is yours and does not feed any third-party model.
  • Is our data 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 how many sources come in. Connecting email, calendar, and a document folder is quick; what takes time is deciding which routines the agent owns and at which autonomy level.

Secure AI Agent

Start with a Secure AI Agent in your company's routine

Talk to our specialists and see how to adapt this AI Agent to your processes, systems, and needs.