01 · todayshipping
The teammate
Point it at a target you're authorized to test; get back a ranked, de-noised threat assessment with the evidence behind each finding.
AI recon & triage · you decide Your scanner found 500 alerts.
Your scanner found 500 alerts.
Three of them matter.
Xseth runs the recon — Subfinder, Naabu, HTTPX, Nmap — then a security-tuned LLM ranks the noise out into a prioritized threat assessment, with the evidence behind every finding. In minutes. You decide what's real.
Hosted today · self-hosting on the roadmap
triagingacme.example.com≈ 4m
Raw scanner output
~500 alerts
AI triage
▸ what matters
- HIGHExposed Redis datastore:6379
- MEDJenkins login exposed:8080
- MEDDeprecated TLS enabled:443
500 raw →3 ranked · noise cut, evidence kept
// no demo flow · the real console
What lands on your screen
Every finding ranked, with the evidence and the fix beside it. This is the actual assessment — not a slide.
app.xseth.com/dashboard
Threat Assessment
ID: xseth_demo_8829F
Target:acme.example.comHIGH
Executive Summary
Xseth ran its recon pipeline (Subfinder → Naabu → HTTPX → Nmap) across the target and triaged the results. From the outside it observed an unauthenticated datastore reachable on the public internet, an exposed CI/build login surface, and deprecated TLS on the main site — ranked here by likely impact. Findings are based on observed evidence, not active exploitation; validate them before acting.
Findings (3)
1. Exposed datastore — Redis reachable on the internet
HIGHAsset
203.0.113.45:6379 (db-staging.acme.example.com)
Impact
A datastore reachable from the public internet with no transport security. If it is not authenticated, anyone who can reach it could read or modify data.
2. Exposed CI/build login surface (Jenkins)
MEDIUMAsset
198.51.100.12:8080 (build.acme.example.com)
Impact
A CI/CD login page exposed to the internet. If it accepts weak or default credentials, an attacker could reach the build pipeline and its secrets.
3. Deprecated TLS enabled on the main site
MEDIUMAsset
www.acme.example.com:443
Impact
Outdated TLS protocols weaken transport security and commonly fail compliance checks (PCI DSS, SOC 2).
XsethPro
9:41
Threat Assessment
ID: xseth_demo_8829F
Target:acme.example.com
Risk:HIGH
Critical Findings
1. Exposed datastore — Redis reachable on the internet
A datastore reachable from the public internet with no transport security. If it is not authenticated, anyone who can reach it could read or modify data.
2. Exposed CI/build login surface (Jenkins)
A CI/CD login page exposed to the internet. If it accepts weak or default credentials, an attacker could reach the build pipeline and its secrets.
3. Deprecated TLS enabled on the main site
Outdated TLS protocols weaken transport security and commonly fail compliance checks (PCI DSS, SOC 2).
// what you get today
A recon & triage teammate
Continuous penetration testing, without the consultants.
Not an autonomous attacker — a force multiplier for the engineer you already have. Honest about what it does, and about what it doesn't.
Less noise, not more
A security-tuned LLM ranks and de-noises raw recon, so one engineer reads signal instead of wading through scanner output.
You stay in control
AI plans the recon and triages the findings. Every result carries the evidence behind it — you decide what is real and what matters.
Minutes, not weeks
Submit a target you are authorized to test and get a prioritized threat assessment back — usually in under five minutes.
Nothing hidden
It runs the tools you already trust — Subfinder, Naabu, HTTPX, Nmap — and shows you exactly what it ran and why.
// scanner vs. engine
It already has a brain
A scanner runs a checklist. Xseth keeps a model of the target and reasons over it — that cognitive core is built and running today. The autonomy is where we're going, one capability at a time, behind controls.
02 · the brainalready built
The cognitive core
Under the hood Xseth keeps a live world-model of the target, chains low-severity findings into real attack paths, and runs a bounded decide-loop. The difference between a scanner and something that reasons.
world-modelattack-chainingOODA loop
03 · the visionroadmap
The engine
An autonomous AI pentesting engine that acts like a hacker — goal-directed, adaptive, chaining to impact — always scope-bound, approval-gated, and audited. The brain is built; the hands come one capability at a time.
See the engine// A2 · world model
liveWhat it sees
Hosts, subdomains, services and endpoints projected into one persistent graph the agent reasons over.
// A4 · attack path
highWhat it chains
Exposed CI panel + reused credential → pipeline access.
- 1
build.acme.io:8080
Exposed Jenkins login surface
- 2
ci pipeline
Weak/default credential → pipeline access
- 3
build environment
Reach secrets staged in the build
// A3 · agent loop
boundedWhat it decides
budget1 / 2 spent
0
continue
Naabu surfaced a new host — one focused Nmap wave is worth the cost.
1
stop
Picture is complete and the step budget is reached. Halt cleanly.
// in good company
Backed by NVIDIA Inception & Startup Grind
Xseth was selected into two of the programs that back the world's most ambitious startups — the same networks behind companies you already know.
NVIDIA Inception
MemberSelected into NVIDIA Inception
NVIDIA's program for cutting-edge AI startups — putting Xseth alongside the world's most ambitious AI companies, with access to NVIDIA's accelerated-computing stack, technical expertise, and go-to-market support.
Learn more
Startup Grind
MemberPart of Startup Grind
The world's largest community of startups, powered by Google for Startups — connecting Xseth to founders, mentors, and investors across hundreds of cities worldwide.
Learn more// frequently asked
Questions, answered
Straight answers to what teams ask before their first scan.
What does Xseth do, exactly?
Xseth runs the recon — Subfinder, Naabu, HTTPX, Nmap — then a security-tuned LLM triages the output into a prioritized threat assessment with the evidence behind each finding. You review and decide what is real. It is recon and triage, with a human in the loop.
Is my source code sent anywhere?
No. Only recon metadata — subdomains, ports, banners, HTTP and Nmap evidence — is processed by our LLM provider to generate the assessment. Never your source code or secrets, and only for targets you are authorized to scan. Self-hosting is on the roadmap.
How long does an assessment take?
Usually under five minutes from submitting a target to a ranked threat assessment, depending on the size of the attack surface.
What am I allowed to scan?
Only targets you are authorized to test. SmartGate refuses hospitals, governments, schools, and other off-limits targets before a single packet leaves the box.
Does Xseth replace a penetration test?
No. Xseth is a force multiplier, not a compliance pentest. It makes one engineer faster and cuts false positives — it supplements human-driven and compliance-grade testing, it does not replace it.
Become a design partner.
We're onboarding a small group of technical teams who'll self-evaluate, run real targets, and shape what Xseth becomes. Early access, direct line to the founders.