Secure AI Agent · Email and Lifecycle

AI applied to revenue from your list

A specialist configured to build lifecycle flows, segment by RFM, diagnose deliverability, and keep the CRM clean — with your approval before anything goes out.

See plans

Companies that trust UPX

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

Capabilities

What the Lifecycle Agent can do

Main areas of work for the Email and Lifecycle Marketing AI Agent in your operation.

Lifecycle flows

Designs welcome, abandoned cart, post-purchase, and win-back with the trigger for each step.

RFM segmentation

Splits the list by recency, frequency, and value and names each segment.

Copy with A/B tests

Drafts the variants and declares the hypothesis and decision metric for each test.

Deliverability diagnosis

Checks SPF, DKIM, and DMARC and flags what is hurting domain reputation.

Lead scoring

Scores contacts by the criteria the team defined and shows the math.

List hygiene

Detects duplicates, invalid addresses, and contacts without valid opt-in.

Skills

Capabilities that compose the specialist

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

Flow design
Builds the sequence with trigger, wait, and exit rule for each step.
Audience segmentation
Splits the list by behavior and returns the size of each segment.
Delivery audit
Checks domain authentication and isolates the cause of bounces.
How it works

From segment to send, with approval before anything goes out

Connect the CRM and the sending platform, define what the agent can do, and let the work happen within your operation's limits.

01

Connect CRM and sending platform
The agent works where the list already lives.Connect HubSpot or Mailchimp, the list spreadsheet, and the support channel so the Secure AI Agent has access only to what it needs to segment and prepare campaigns.

02

Ask for the work
Talk to the agent in natural language.Request the win-back flow, the RFM cut of the list, or the deliverability diagnosis. The agent understands the context, applies the configured skills, and follows the operation's rules.

03

The agent prepares. You approve the send.
No message goes out on its own.The agent segments, drafts, and configures within the defined permissions. Sending a campaign, changing a live flow, and deleting a contact still require human approval.

Integrations

Connected to the platforms where your list already lives

The Lifecycle Agent can query contacts and run tasks in the systems your team already uses.

Flow

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

From a raw contact list to a campaign ready for approval, following your operation's rules and permissions.

Inputs

  • Contacts and interactionsAPI
  • Purchase historyCSV
  • Opt-in policyDOC

Processing

Secure AI Agent

Processing the task

  • Read
  • Segment
  • Draftrunning
  • Configure
Skill appliedRules verified

Output

Completed

Campaign prepared

  • Segment with size
  • Variants for testing
  • Flow awaiting approval

Control

You define how far the Agent can act

Different actions can operate with different autonomy levels, always within your operation's rules.

  1. 1

    Query

    Reads contacts and interactions and answers with the reference.

  2. 2

    Prepare

    Builds the segment, the variants, and the flow.

  3. 3

    Request review

    Waits for validation from whoever owns the communication.

  4. 4

    Execute

    Performs the action within the defined limits.

Levels are configured per type of action, according to each operation's policy. Sending a campaign, activating a live flow, and deleting a contact always stay under human approval — a send cannot be undone.

Get started

Put a Secure AI Agent to work.

Start on the platform or choose the plan that fits the pace of your operation.

See plans
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: 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 Lifecycle Agent

What teams usually ask before putting an agent to support marketing automation.

  • Does the agent send campaigns on its own?

    No. It segments, drafts, and configures the flow, but sending requires approval from whoever owns the communication. A send cannot be undone, so this gate is the default and covers email, WhatsApp, and SMS.
  • Does it work with any email platform?

    In connected HubSpot and Mailchimp the agent works live, with your approval. On other platforms it delivers a load-ready spec — segment, copy, and flow configuration — because promising live operation without an integration would promise what the platform does not expose.
  • How does it handle consent and unsubscribes?

    The list is personal data: the agent checks for valid opt-in before adding a contact to a flow, honors unsubscribes, and flags records without a clear legal basis. It does not work around consent to grow reach.
  • What does it do for deliverability?

    It checks domain authentication (SPF, DKIM, DMARC), reads bounces, and isolates the cause — invalid address, reputation, content. The DNS fix is delivered as a diagnosis; publishing the record stays with whoever administers the domain.
  • Is list 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 the platforms involved. The starting point is connecting the CRM and the sending tool, then expanding the scope as the first flows get approved.

Custom agents

We build and manage the agent for your list

From the RFM cut to an approved flow: we build the agent that pulls revenue from your list without burning domain reputation.