This page says what this site is, what in it is invented, what was checked and when, where the ideas come from, and which sister sites cover the subjects next to this one.
What this site is#
Guardrails Engineering teaches one idea from the ground up: a prompt asks, a guardrail enforces. It starts from the checks every backend already has (validation, business rules, access lists, middleware, policy engines) and climbs to layered, enforceable controls around an agent built on a probabilistic model: trust labels, input checks, a tool gate, output checks, an egress allowlist, versioned rules, model-based checks that flag, and a person who decides.
It teaches defense. Every attack text on the site is short, synthetic and aimed only at the site's own scripted stand-in, and it is shown only as far as the control that stops it needs. There is no recipe against a real product, no real exploit and no real target.
The author is Sam Muthu. The site is a map to adapt, not a standard: the guard ids, the four places and the page order are one way of dividing the subject, and no standards body defined them.
What is synthetic#
This is an illustrative reconstruction for teaching. It follows the shape of a real project by the author, but the cases, the rules, the fields, the provider, the attack texts and every number are invented. Nothing here reports the quality or the security of a real system or model.
| Thing | Status |
|---|---|
| The insurer, the brokers, the roof-data provider, the underwriters | Invented; never named; roles only |
The policy fixture UW-GUIDE (2026.2, 2025.4) and its rules | Illustrative; not insurance practice; no real insurer's criteria |
Cases UW-G01 to UW-G14, submissions SUB-2001 to SUB-2014 | Invented for this site |
| Hosts, emails and identifiers | .example domains and the marker 000-00-0000 only |
| The agent | A scripted stand-in in standard-library Python; no model call, no key, no network |
| Every count on the site (records sent, trials, rates) | Produced by the scripted stand-in; shows how a control works, not how often a real model is fooled |
The agent here is a scripted stand-in. The obedient variant is fooled every time by construction, so the results on this site show how each control works, not how often a real model is fooled or how good any model is.
How the facts were checked#
Statements about a named product, protocol or standard come from its own documentation, read on 2026-11-17, and each claim is logged with its URL and date in the repository's docs/facts/ folder, one file per page. Where a page did not say something, the site says "the documentation read here does not say". Facts that looked surprising (a moved documentation page, a deprecation, an engine marked experimental) were fetched a second time by a different reader before publishing. No prices, no rankings, no "best".
The Python code shown on the pages comes from the example in the repository (examples/uw-guardrails/), and every output shown was pasted from a real run. Code in Java, Rego, YAML or a framework's configuration is labelled "documented shape; not run here", and its shape comes from the documentation read that day.
Diagram: Where each kind of statement on this site comes from
Read left to right. Statements about tools and standards come from their own documentation, read on one date and logged. Results come from runs of the example code, pasted as they printed. Designs are this site's own and are called designs. Every number from the example is synthetic.
- Tools and standards
- Their own documentation: Each claim logged with its URL and date in the fact files.
- Results
- Runs of the example: Standard-library Python with a scripted stand-in; no model call.
- Designs
- This site's arrangement: The four places, the five-step anatomy, the trust label read by the tool gate.
- Labelled as
- Synthetic, illustrative: No result reports the quality or security of a real system or model.
Sources#
Primary sources read for this site, grouped. Vendor documentation changes often; the date read is 2026-11-17 for all of them.
| Source | Used on |
|---|---|
| OWASP Top 10 for LLM Applications and LLM01 Prompt Injection | Prompt injection, Frameworks |
| NIST AI Risk Management Framework | Frameworks |
| Open Policy Agent documentation | Before AI, Policy as code, Frameworks |
| Guardrails AI repository | Frameworks, Input checks |
| NeMo Guardrails documentation | Frameworks, Tool controls, Input checks |
| Promptfoo documentation | Frameworks, Testing |
| A provider's moderation guide | Frameworks, Output checks |
| A provider's guide on mitigating jailbreaks and prompt injection | Frameworks, Prompt injection |
| A coding agent's sandboxing documentation | Defense in depth |
| Spring Security architecture, Jakarta Bean Validation, PostgreSQL row security | Before AI, Input checks |
What is original here, and what is not#
Ideas with an author are attributed where they are used. The confused deputy is Norm Hardy's, from a 1988 paper. Defense in depth, least privilege, allowlists, taint checking, policy decision points and idempotency keys are long-standing engineering ideas with no single owner on this site. The split of prompt injection into direct and indirect follows the OWASP list and provider documentation.
What this site adds is the arrangement: the four places plus the network edge as a frame for every check; the five-step anatomy of an injection (placement, delivery, adoption, action, payoff) with the rule that wording only acts at adoption; the trust label read by the tool gate; the policy gate as one comparison that stops several different attacks; and the blast radius computed from holdings with the agent assumed fooled. These are designs for teaching. Where the site proposes a design, it calls it a design.
No prose, example or figure was copied from any source. The diagrams are original.
Sister sites#
This site is one of a series of guides on engineering with AI agents. Each owns one subject and links the others where the subjects meet.
| Site | Owns |
|---|---|
| Prompt Engineering | How instructions are written, composed and versioned |
| Context Engineering | What the model can see now: selection, retrieval, budget |
| Memory Engineering | Durable information and saved state |
| Agent Communication | Messages between agents; A2A and MCP |
| Observability Engineering | Logs, metrics, traces, audit events and replay as evidence |
| Tools Engineering | Callable capabilities: schema, execution, MCP tools |
| Structured Output Engineering | Typed contracts: shape, validation, repair, evolution |
| Agent Orchestration | The control plane: what runs next, under which condition |
| Agent Reliability | Acceptable outcomes despite failures, retries and load |
| Eval Engineering | Measurement: graders, golden sets, judges, release gates |
| Harness Engineering | The runtime around a model call |
| Diff to Deploy | Shipping a change with coding agents: hooks, review, CI |
What this is not. This site is not a governance guide. Governance (who is accountable, which controls must exist, who may grant an exception) is the organization's own system; this site describes only the part of it that a guardrail depends on.
Run it yourself#
The example needs Python 3 and nothing else: no model, no key, no network. From the repository root, python3 examples/uw-guardrails/run_guards.py --all prints every case under the warning-only profile and with every guard, and python3 -m unittest inside that folder runs its tests. The labs on the pages run in the browser on data generated from the same code, and store nothing.