CyberfactorsCyberfactors

Stop burning AI tokens on code that won't break

Cyberfactors forecasts which functions will break, so verification budget lands only where it counts.

A common pattern: blanket AI review spend
Low-risk changes (safe code)70% of tokens
High-risk changes (where it matters)30% of tokens

An illustrative model, not a measurement of your repository. Basis: our internal modeling of blanket-review costs, scaled to a team shipping about 50 pull requests a week. Your split will differ.

Most verification spend lands on code that won't break

The same expensive scans run on every change, regardless of risk. Slow pipelines, bloated bills, buried signals. The figures below are an illustrative model, not a measurement of your repository.

~0M
tokens a year on low-risk reviews, ~50 PRs/week (illustrative model)
Blanket AI reviews burn tokens

Deep AI review on every PR, config tweaks included, spends tokens where there is nothing to find.

0%
of scan time on low-risk code, in the model
Pipelines slow to a crawl

Full scans on every commit add minutes to every merge.

0×
as many low-risk flags as real ones, in the model
Real risks get buried

When everything is flagged, the dangerous changes wait in line.

Illustrative model: ~2,600 PRs a year at 20-50k AI-review tokens each, with ~70% landing on low-risk changes. That 70% share matches our public Pillow validation, where 833 of 1,168 analyzed functions scored low-risk. Direction, not a measurement, forecast, or guarantee for your repository.

How Cyberfactors Works

Sits upstream of your verification tools. Scores each change by risk so expensive checks run only where they matter.

Risk signals
01

Analyze risk signals

Every change is scored on research-backed risk signals, not just complexity or line count.

Defect likelihood
02

Prioritize by defect likelihood

A risk score grounded in models validated across 21 open-source projects.

INPUTAI agentLinterSec scanQuality bot
Logic dispatcher
03

Route verification intelligently

High-risk gets deep review and security scans. Low-risk passes with light checks.

One filter sits before your expensive checks.

The Pre-Check Layer scores every change before your expensive verification steps run: budget stays on the changes that can actually break.

Runs inside your existing pipeline

Drops into GitHub, GitLab, and Jenkins with a single step YAML addition.

Routes your existing tools by risk

Decides when Snyk, Sonar, and AI reviews trigger based on risk probability.

Your code stays in your perimeter

Analysis runs in your CI; we receive function-level risk scores only. Source never leaves your environment.

First risk scoring in under five minutes

From workflow install to first risk scoring in under five minutes. Repo evaluation needs no install at all.

Pipeline
Code submission
Pull request #442
Status: unknown
Cyberfactors
Risk scoring analysis
Verification suite
Snyk, Sonar, AI review
Risk signal: high
Supported languages
CC++GoJavaJavaScriptTypeScriptPythonRubyRustSolidityPHPCrystal

Other languages can be added on request.

What you get from scoring risk first

Know which changes carry real risk, and every downstream tool gets sharper.

Focus QA on the changes that matter

Your best reviewers and deepest tests go to the changes most likely to defect.

Cut AI token spend

Score before you spend. Without risk scoring, ~70% of AI review tokens land on changes that won't break.

Catch more production escapes

Flag the riskiest changes early and catch what blanket scanning misses.

Fit into your existing workflow

Drops into your CI/CD pipeline as a pre-check. No tool replacement, no migration.

Built on published research, not marketing claims

Grounded in peer-reviewed research into cognitive and behavioral factors in software quality. Validated across real-world critical software, not toy benchmarks.

0%
PR AUC improvement

relative gain over code-metric baselines: PR AUC 0.49 to 0.65, 21 OSS projects

0+
Vulnerabilities reported

by our team, including officially recognized CVEs. See them all below ↓

0
Open-source projects validated

the evaluation corpus behind every number on this page

Defect prediction accuracy
Traditional code-metric modelsPR AUC 0.49
Cyberfactors (human-factor models)PR AUC 0.65 · +38% relative

PR AUC, higher is better. Same 21 open-source projects as above.

Defects found before attackers did

Real bugs our team reported and got patched upstream, in projects that ship on billions of devices.

5
CVEs assigned
8
Patched upstream
23
Reports filed
Git
patched

Three out-of-bounds memory access issues (7 patches)

Git is the 2nd most critical open-source project by Google's criticality score. Patches coordinated with the Google security team after a PoC in mailinfo's double-quote / RFC822 comment handling.

GNU Tar
CVE-2021-20193patched

Memory corruption in GNU Tar

GNU Tar is a core utility for archive creation/extraction, shipped in virtually every Linux distribution.

Toybox
acknowledged

Stack-buffer-overflow in toybox tar

Toybox ships in every currently-supported Android version and most home routers; practically all Android phones and many routers were exposed.

See your repo's risk profile in minutes

Submit your repository URL and get a full risk report. No integration required.

01
Share your repo URL

Illustrative demo, not a real repository. Analysis runs in your CI; only risk scores are stored.

02
Cyberfactors analyzes risk signals

Cognitive and behavioral signals evaluated per function.

03
Receive a prioritized risk report

See which functions need attention and why, with actionable scores.

Request your repo evaluation
cyberfactors-cli
sample output (illustrative)

Frequently asked questions

Stop reviewing everything. Start prioritizing risk.

See which functions carry real risk before your next release.

Free evaluation, no integration needed. The product itself is one YAML step.