> For the complete documentation index, see [llms.txt](https://docs.probe.splx.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.probe.splx.ai/ai-red-teaming/remediation.md).

# Remediation

The Remediation helps you take Probe’s findings and turn them into stronger defenses. With [**Prompt Hardening**](#prompt-hardening), you can reinforce system prompts to reduce vulnerabilities and improve resilience against adversarial inputs. With [**Policy Generator**](https://docs.probe.splx.ai/ai-red-teaming/remediation/policy-generator.md), you can automatically turn Probe Run insights into a clear, ready-to-use protection strategy.

#### Prompt Hardening

* Strengthens system prompt based on selected Probe results.
* Continuously refine protections as threats evolve.
* Backed by our red-teaming expertise.

{% hint style="info" %}
Prompt Hardening can also be paired with [**Policy Generator**](#policy-generator), adding an extra layer of defense that detects and responds to malicious inputs during live interactions.
{% endhint %}

#### Policy Generator

* "From Probe to Guardrail"
* Creates a template policy for a guardrails.
* Fine‑tunes policy template configuration based on selected Probe Run results.
* Backed by our red-teaming expertise.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.probe.splx.ai/ai-red-teaming/remediation.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
