Skip to content
Cisent Message us on WhatsAppMessage us

Cybersecurity powered by our own AI.

AI Technologies

Cybersecurity ecosystem · Made in Chile

Cisent tests your defenses, contains attacks in real time, documents every incident and trains your team. Everything runs on AI models trained by Cisent.

  • ReasonsWith our own models, no outside AI provider in between.
  • BlocksOn its own; anything with impact, your team approves.
  • RecordsEvery action taken.
  • LearnsFrom every attempt: each new attacker technique becomes a defense rule.
  • DefendsIn real time, alongside your EDR, your firewall and every source you connect.
  • TeachesYour team to respond to every alert.

Detects across four dimensions.

Attacks no longer arrive only in writing: Cisent reads, sees and listens.

  • Text
  • Image
  • Video
  • Audio

Why trust Cisent

Programs

  • Cyber Verification Program
  • Inception Program
  • JumpStart

How it works

Manthys judges. Husker decides.

The four products feed each other inside Husker, our own agentic layer. Red Team finds the gap, Defense blocks it, Report keeps the evidence and Cisent Iroh turns every case into learning for your team.

  1. Sentinel Red TeamFinds the gap.
  2. Sentinel DefenseBlocks it.
  3. Sentinel ReportKeeps the evidence.
  4. Cisent IrohTurns every case into learning for your team.

The foundation, in three layers

  • CisentThe system that carries out the actions and keeps the evidence.
  • HuskerThe agentic layer. It acts within the limits your team approves and records everything.
  • ManthysFour families of models trained by Cisent. Mind reasons, Sentinel defends, Nova brings the scale and Reflex filters.

Features

Features of the ecosystem.

Connects to what you already have.

Works alongside your EDR, your firewall and every source you connect; it doesn't replace them.

We don't train on your data.

Not even anonymized.

Models trained by Cisent.

Cisent trains and operates them; how they work doesn't depend on foreign providers' usage policies.

Agents with limits.

They act on their own where an action can be undone and ask before anything with impact. If an action can't be recorded, it doesn't run.

They say “I don't know” when they don't know.

The models flag doubt instead of making up a fact: Mind Ultra 2 fabricates 60% less than its base.

Made in Chile.

Development, operations and support in Chile, in Spanish, with local regulation as the starting point.

AlternativeSolvesUnresolvedCisent
Traditional SIEM and EDR They detect and alert on known rules. Someone still has to investigate, decide and report. Defense investigates and acts; Report documents.
General-purpose AI assistants They answer questions and write. They don't operate inside your network and aren't built for offensive security. Models trained for cybersecurity.
Annual pentest or one-off consulting A snapshot of your defenses at one moment. Gaps change between one review and the next. Red Team tests continuously.
Manual incident reporting The report, if there's time and people. Seven steps against deadlines measured in hours. Report has it ready in parallel with the response.

Products

Four products on one foundation.

Defense, Red Team, Report and Cisent Iroh share models, agents and evidence. What Red Team uncovers, Defense blocks; what Defense contains, Report documents.

Sentinel Defense

Agentic defense in real time.

Detects, assesses and blocks attacks alongside your EDR, your firewall and every source you connect. It acts on its own only where an action can be undone, and asks before anything with impact.

  • Detection across four dimensions: text, image, video and audio.
  • Immediate blocking of attacking IPs and intrusive connections.
  • Every new attacker technique becomes a defense rule.
  • Connectors for FortiGate, pfSense, OPNsense, UniFi and more.
Explore Sentinel Defense

Sentinel Red Team

Continuous ethical hacking.

AI agents attack your systems with your authorization and within the scope you define, to find the gaps before an attacker does.

  • An assessment of your defenses before deploying Sentinel.
  • Ongoing testing, not one audit a year.
  • New attack patterns to train your defense.
  • Support for the reviews and drills that Chile's Law 21.663 requires of critical infrastructure operators (OIV).
  • Runs on Manthys Sentinel models trained for red teaming.
Explore Sentinel Red Team

Sentinel Report

The report on every attack, while it's still open.

Gathers and seals the evidence and drafts the report for each audience. For any company, whether or not Law 21.663 applies to it.

  • First report in 3 minutes.
  • Evidence sealed with a hash chain.
  • Reports for the board, IT team, insurer and ANCI.
  • Works in parallel with containment, not after it.
Explore Sentinel Report

Cisent Iroh

The agent that trains your team.

Talks with your team, explains alerts and incidents and teaches how to respond. It's an add-on to any of the other three products.

  • Explains attack techniques and response measures in plain language.
  • Trains technical and non-technical staff.
  • Uses the same models as the rest of the ecosystem.
Explore Cisent Iroh

Manthys

Models trained by Cisent, measured on third-party benchmarks.

Manthys is four families of models. Every figure carries its source.

Manthys Mind · generalist

It says “I don't know” when it doesn't know.

60%

less fabrication than its base.

Mind Ultra 2 on SimpleQA: 36.7% incorrect answers vs. 90.9% for its base.

Manthys Sentinel · cybersecurity

It reads the attack like an analyst.

72.44F1

on ATT&CK techniques; the best figure published by another specialist is 49.1.

Sentinel Ultra 2 on CTI-Bench (CTI-ATE, 60 reports). 49.1: Cisco's Foundation-Sec-8B-Reasoning (arXiv 2601.21051).

Manthys Nova · the largest scale

It flags its doubt. So you can verify.

22.7%

of its reasoning traces state uncertainty.

Nova C 2, CTI-MCQ reasoning traces (150 questions).

Manthys Reflex · decisions

It decides what deserves the judge's attention.

Reflex C 2 reads every log and answers with a decision and its probability; it doesn't write.

27of 28

injected attacks detected in 48 hours of real traffic, measured blind.

A lab firewall, 7,401 windows. False alarms per day: 3 on “port scan”, 5 on “alert the judge” and 0 on brute force.

Explore Reflex

Science and research

Our entire research process, in depth.

See the publications

Getting started

Three ways to start.

An assessment with Sentinel Red Team.

We assess your current defenses and hand you the vulnerabilities we find, before implementing anything else.

Defense on top of what you already have.

Sentinel Defense connects to your firewall, your EDR and every source you have, with the action rules your team approves.

Reports from the next incident on.

Sentinel Report is ready to document and report the next attack.

The first days

  1. Scoping meeting
  2. Connecting your systems
  3. Rules approved by your team
  4. First report

Team

Meet our founders.

Founders

Cisent in the real world

How we solve your challenges.

Investigating an alert.

An alert comes in and it's unclear whether it's an attack. Sentinel Defense gathers logs, traffic and captures; Manthys Sentinel reads them like an analyst and maps the technique in ATT&CK; Husker acts according to the impact.

Sentinel Defense · Manthys Sentinel

Explore Sentinel Defense

Containing ransomware.

A machine starts encrypting files. Defense cuts the intrusive connection, blocks the attacking IP and freezes the evidence on the spot; before isolating a machine in your organization, it asks. Report documents in parallel.

Sentinel Defense · Sentinel Report

Explore Sentinel Defense

Reporting an incident.

If the law applies to you, the early warning to ANCI is due within 3 hours; the board and the insurer also want their report. Sentinel Report gathers the sealed evidence and drafts each version; your team reviews and sends.

Sentinel Report · Manthys Sentinel

Explore Sentinel Report

Testing your defenses before an audit.

Red Team attacks with your authorization and within the agreed scope. What it finds becomes Defense rules and is documented by Report.

Sentinel Red Team

Explore Sentinel Red Team

Training the team after an incident.

Cisent Iroh explains what happened, which technique was used and how it was handled, in plain language.

Cisent Iroh

Explore Cisent Iroh

Questions

Frequently asked questions.

Management

What does my company sign up for?

Products contracted as a service: Sentinel Defense, Sentinel Red Team, Sentinel Report and Cisent Iroh. The Manthys models are not sold separately.

Is it useful if Law 21.663 doesn't apply to my company?

Yes. Report documents every attack for the board, the team and the insurer; if the law applies to you, it also prepares the reports to ANCI.

Does it replace my team or my security provider?

No. It works alongside your EDR, your firewall, every source you connect and your team, and asks before any action with impact.

CISO and IT

What does it integrate with?

FortiGate, pfSense, OPNsense, UniFi and more, through connectors audited by Cisent.

What does Husker decide without asking?

What can be undone: blocking an external attacking IP, cutting an intrusive connection and freezing the evidence. Blocking an internal machine or changing a rule, it asks first.

How do Manthys and Husker split the work?

Manthys judges: the models analyze and classify. Husker decides: it acts within the approved limits and records everything.

Is there an outside AI provider in between?

No. Our own models, with no outside AI provider in between. We don't train on your data. Not even anonymized.

Legal and compliance

Do you use our data for training?

No. We don't train on your data. Not even anonymized.

Which deadlines does Report cover?

Those set by the Law 21.663 regulation: early warning within 3 hours, second report within 72 hours (24 if an essential service is affected), action plan within 7 days and final report within 15 days.

Book a meeting with the Cisent team.

Tell us what your organization needs to protect. We'll reply on WhatsApp and set up the meeting.

Message us on WhatsApp and let's book a meeting

or write to info@cisent.ai