# How to add guardrails to an LLM app

To add guardrails to an app built on a large language model (LLM), list its risks, write a policy for each, check every input, output and tool call, choose an action per policy, log verdicts and test with attacks.

## Steps

1. **List the risks.** Write down what must not happen in this app: a leaked customer record, a harmful answer, an agent deleting data. Start from what the app can read and do.
2. **Write policies in plain language.** One rule per risk, worded as something the AI writes or does: "The assistant reveals another customer's order." See [guardrail policy](/glossary/guardrail-policy).
3. **Put a check at three points.** On inputs before the model call, on outputs before the user sees them, and on tool calls before they run. See [input and output guardrails](/glossary/input-and-output-guardrails).
4. **Choose an action per policy.** Block what is dangerous, redact personal data, hold a risky tool call for approval, and flag what only needs review. See [guardrail actions](/glossary/guardrail-actions).
5. **Log every verdict.** Record which policy fired, on what, and what was done. Incident review and tuning both depend on it.
6. **Test with attacks.** Run jailbreaks and prompt injections against the whole app before launch and after each change. See [how to red team an LLM](/glossary/how-to-red-team-an-llm).
7. **Watch false positives.** Read a sample of what was blocked, and narrow or reword any policy that stops normal requests. See [false positives in guardrails](/glossary/guardrail-false-positives).

## Common mistakes

- Checking only inputs. A harmless prompt can still produce a harmful answer.
- Putting the rules in the system prompt and stopping there. A prompt asks, and nothing enforces it.

## With White Circle

Integration is one API, or middleware, that works with any model or setup and takes about five minutes. [Control](/products/control) then enforces your plain-language policies on every input, output and tool call.

