Secure AI Agent · Human Resources

AI applied to HR routines

A specialist configured to organize applications, answer questions about internal policies, and coordinate schedules within the rules and permissions defined by your company.

Companies that trust UPX

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

Capabilities

What the HR Agent can do

Main areas of work for the HR AI Agent in your operation.

Application screening

Compare applications against role requirements and organize the profiles.

Policy questions

Answer questions about benefits and internal processes, with the source.

Scheduling

Find common slots and coordinate interviews across multiple calendars.

Engagement surveys

Run short surveys and summarize how teams are feeling.

Personnel documents

Organize and verify information from department documents.

Operational queries

Answer the team's questions based on authorized data.

Skills

Capabilities that compose the specialist

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

Candidate screening
Compares applications against role requirements and organizes the profiles.
Internal policy base
Answers questions about policies, benefits, and internal processes.
Cross-calendar scheduling
Finds common slots and books meetings across several people.
How it works

From request to delivery, with decisions always human

Connect your people systems, define what the agent can do, and let organizing and preparation happen within your operation's limits.

01

Connect your people systems
The agent works where HR already keeps records.Connect the recruiting system, the policy base, and calendars so the Secure AI Agent has access only to what it needs to execute each task.

02

Ask for the work
Talk to the agent in natural language.Request a screening, a scheduling, or a policy lookup through the available channels. The agent understands the context, applies the configured skills, and follows the rules defined by your company.

03

The agent organizes. HR decides.
From request to delivery, with accountability preserved.The agent queries, organizes, and prepares the material within the defined permissions. Decisions about people stay with the HR team and the responsible managers.

Integrations

Connected to the tools that are part of your HR operation

The HR AI Agent can query information and run tasks in the systems your team already uses.

  • Workday
  • Greenhouse
  • BambooHR
  • Google Calendar
  • Slack

Flow

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

From raw information to organized material, following your company's rules and permissions.

Inputs

  • ApplicationPDF
  • Job descriptionDOCX
  • CalendarsCalendar

Processing

Secure AI Agent

Processing the task

  • Read
  • Compare requirements
  • Organize profilesrunning
  • Propose slots
Skill appliedRules checked

Output

Completed

Material organized

  • Profiles compared to requirements
  • Points of attention flagged
  • Schedule ready for confirmation

Control

You define how far the Agent can act

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

  1. 1

    Query

    Reads the policy and answers with the source.

  2. 2

    Prepare

    Organizes profiles and proposes slots.

  3. 3

    Request approval

    Waits for validation from the process owner.

  4. 4

    Execute

    Performs the action within the defined limits.

Levels are configured per type of action, according to each company's policy. Hiring, promotion, and termination decisions always stay with people.

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 HR Agent

What HR teams usually ask before putting an agent to work.

  • Does the agent decide who gets hired?

    No. It compares applications against the role requirements and organizes the profiles for the team to assess. Decisions about hiring, promoting, or terminating stay with HR and the responsible managers.
  • Does it reject candidates automatically?

    Not by default. The agent organizes and flags, but the team decides who is rejected. If you configure an automatic filter, it is logged and auditable, and the history shows what was applied to each application.
  • What happens to candidates' personal data?

    Data is isolated per environment and the agent reaches only what permissions allow. Processed content is not used to train UPX models or third-party models, and retention follows your company's policy.
  • Does it connect to the HR system we already use?

    Yes. The agent works in the systems your team already uses, such as Workday, Greenhouse, and BambooHR, plus calendars and email. Permissions define what it can query and where it can execute actions.
  • Are the answers about benefits reliable?

    They come from the policy base your company publishes, with the source indicated for verification. When the agent cannot find a basis, it flags the gap instead of guessing.
  • 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 and your operating rules. The starting point is mapping the routines that consume most of the team's time and configuring the agent for those, expanding the scope as results come in.

Secure AI Agent

Bring a Secure AI Agent to your HR operation

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