NeuroNomixer
  • Home
  • Blog
  • Visual Guides
  • Authors
  • Contact
Sign InSign Up
HomeBlogAuthorsContactPrivacy Policy

© 2026 NeuroNomixer — Built with Next.js & Tailwind CSS

Visual Guides/Guardrails Architecture
Applied AI

Guardrails Architecture

No single filter stops a determined attacker. Toggle four defense layers over a fixed set of attack and benign strings, run them through transparent rule-based classifiers, and watch the block rate and the false-positive rate move against each other. The lesson is computed, not asserted: single layers fail where stacks hold.

Replay one layer alone
Replay all four layers
Inspect a corpus item

Sign in to save progress

Defense in depth, made testable

A guardrail is any check that sits between a request and a consequence. There are four common places to put one: filter the input before the model sees it, constrain the model with a system-prompt policy, filter the output after generation, and gate the actual actions the model can take. Each catches a different kind of attack and misses others. The only honest way to see this is to run a small designed corpus through them.

Corpus size

16 strings

Attacks

8

Benign

8

Layers

4

Every attack string below is a tame, illustrative example, the benign strings are deliberately authored to trip naive filters so the false-positive pressure is real, and every model response shown is authored for the demo, never generated by a live model. The classifiers are plain pattern rules you can read, not a hidden scoring model.

Build your stack

Turn layers on and off and drag the thresholds. The whole corpus re-runs instantly. Start with a single layer to watch it fail, then stack all four.

Input filter

Lexical, pre-model

Scans the incoming text for jailbreak trigger phrases and blocks when the matched-pattern score reaches the threshold.

1

Lower catches more but over-blocks. Higher is stricter about evidence.

System-prompt policy

Intent, pre-model

Scans the text for references to protected assets (the prompt, keys, instructions) and blocks at its threshold.

1

Lower catches more but over-blocks. Higher is stricter about evidence.

Output filter

Post-model

Scans the response after generation for leak markers, catching attacks whose input text looked harmless.

Tool permissioning

Action gate

Blocks any consequential action (send, delete, transfer) regardless of the text, outside the model.

The tradeoff, live

Layers on

0

Block rate

0%

0/8 attacks

False positives

0%

0/8 benign

02550751000255075100idealFalse-positive rate (% benign blocked)Block rate (% attacks blocked)
Your live config: 0% blocked, 0% false positives
Each single layer alone (fixed reference)
All four layers at threshold 1

The ideal is the top-left corner: every attack blocked, no benign request touched. Every single-layer point sits low, none passes 50% block rate. Stacking layers lifts the block rate, and raising thresholds pulls the point back toward the left.

What each layer caught and missed

Every row is scored by the classifiers for the current stack. The four boxes show which layers blocked it (pink) versus let it through. Click any string to see the matched patterns, the authored response, and why the verdict came out the way it did. Look for the exfiltration attack that only tool permissioning stops.

#Request stringKindLayersVerdict
A1attack
IFSPOFTP
missed
A2attack
IFSPOFTP
missed
A3attack
IFSPOFTP
missed
A4attack
IFSPOFTP
missed
A5attack
IFSPOFTP
missed
A6attack
IFSPOFTP
missed
A7attack
IFSPOFTP
missed
A8attack
IFSPOFTP
missed
B1benign
IFSPOFTP
correct
B2benign
IFSPOFTP
correct
B3benign
IFSPOFTP
correct
B4benign
IFSPOFTP
correct
B5benign
IFSPOFTP
correct
B6benign
IFSPOFTP
correct
B7benign
IFSPOFTP
correct
B8benign
IFSPOFTP
correct
attack blocked (good)
attack missed (bad)
benign blocked (false positive)
benign allowed (good)
← All GuidesNext Guide →