Secure AI Agent · PR and Communications
AI applied to what your company says in public
A specialist configured to write releases with a newsworthiness test, build per-outlet pitches, keep the crisis playbook ready, and inform the team before the rumor — with every figure carrying its period and source.
Companies that trust UPX
Capabilities
What the Communications Agent can do
Main areas of work for the Corporate Communications AI Agent in your operation.
Release with newsworthiness test
Drafts the release and states why it is — or is not — news for the press.
Per-outlet pitch
Adapts the angle and length of the approach to what each newsroom covers.
Crisis playbook
Keeps holding statements ready per scenario, for immediate approval when needed.
Internal communications
Builds the manager-first cascade, so the team knows before reading it in the press.
Spokesperson prep
Preps talks, op-eds, and interviews with verified figures and the source for each.
Coverage log
Tracks what was published and consolidates the period with source and date.
Skills
Capabilities that compose the specialist
Skills add specific capabilities to the Secure AI Agent according to the processes it needs to execute.
- Release writing
- Builds the draft with the lede, context, and the proof behind each claim.
- Crisis statement
- Prepares the response per scenario, ready for approval under time pressure.
- Figure verification
- Checks each cited metric and attaches its period and source.
From draft to publication, with the final word always yours
Connect your communications documents and channels, define what the agent can do, and let the prep happen within your operation's limits.
- Connect documents and channels
- The agent works where communications are already written.Connect the document repository, email, LinkedIn, and the internal channel so the Secure AI Agent has access only to what it needs to draft and verify.
- Ask for the work
- Talk to the agent in natural language.Request the announcement release, the pitch for a specific outlet, or the holding statement for a crisis scenario. The agent understands the context, applies the configured skills, and follows the operation's rules.
- The agent drafts. You approve and speak.
- No draft goes out on its own.The agent writes, verifies the figures, and organizes within the defined permissions. Sending a release to the press, publishing a statement, and speaking for the company still require human approval.
01
02
03
Integrations
Connected to the systems where your communications are already written
The Communications Agent can query documents and run tasks in the systems your team already uses.
Flow
What goes in, what the agent does, and what comes out
From the raw announcement context to a draft ready for approval, following your operation's rules and permissions.
Inputs
- Announcement contextDOC
- Period figuresCSV
- Outlet listAPI
Processing
Secure AI Agent
Processing the task
- Read
- Verify source
- Draftrunning
- Adapt per outlet
Output
Completed
Draft prepared
- Release with proof for each claim
- Pitch per outlet
- 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
Query
Reads documents and figures and answers with the reference.
- 2
Prepare
Drafts the release, the pitch, and the statement.
- 3
Request review
Waits for validation from whoever owns the communication.
- 4
Execute
Performs the action within the defined limits.
Levels are configured per type of action, according to each operation's policy. Sending a release to the press, publishing a crisis statement, and speaking for the company always stay under human approval — a public statement 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.
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 Communications Agent
What teams usually ask before putting an agent to support corporate communications.
Does the agent send releases to the press on its own?
No. It drafts the release, tests newsworthiness, and builds the per-outlet pitch. Sending to the press and speaking for the company stay under the approval of whoever owns communications — a public statement cannot be undone.Does it guarantee the story gets published?
No. The agent improves the material and the angle of each approach, but publishing is the newsroom's decision. The page does not promise earned media nor outlet relationships.What is the newsworthiness test?
An honest check before sending: the agent states why a journalist would care — and, when they would not, says so instead of writing a release the newsroom will ignore.How does it handle figures that go to the press?
Every cited metric carries its period and source, verified before it enters the draft. The agent does not round or project to make a sentence stronger; when the data does not exist, it flags the gap.How does the crisis playbook work?
The agent keeps holding statements ready per scenario, so approval under time pressure is only review, not writing. The content is prepared beforehand; the decision to publish always belongs to the moment.Are company documents used to train models?
No. Content processed by Secure AI Agents is not used to train UPX models or third-party models.How long does it take to go live?
It depends on the existing material. The starting point is connecting the document repository and loading the crisis scenarios, then expanding the scope as the first drafts get approved.
Custom agents
We build and manage the agent for your communications
From the release to the crisis playbook: we build the agent that prepares what the company says, with figures and sources.