> For the complete documentation index, see [llms.txt](https://waf-doc.inext.checkpoint.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://waf-doc.inext.checkpoint.com/how-to/use-automatic-tuning-suggestions.md).
# Use Automatic Tuning Suggestions
Check Point WAF's Contextual Machine Learning engine analyzes suspicious events and surfaces **Tuning Suggestions** — each with an AI-recommended verdict (**Malicious** or **Benign**), the reason behind it, and a sample of the actual attack data. You confirm the verdict, and the WAF reaches high accuracy faster — without investigating every event from scratch.
Find it under **Policy > Assets > *****your asset***** > Learn** tab.
### What the WAF does behind the scenes
The WAF learns on its own from traffic, and reaches even better accuracy when a human confirms its conclusions — an AI process known as **Supervised Learning**:
* **Groups** related events into one case, by **URI** (attacks on the same URL) or by **Source** (one IP across several URLs) — so you review cases, not thousands of events.
* **Analyzes** each case in context: matched indicators, severity, event and source counts, and payload contents.
* **Recommends** a verdict, a plain-language reason, and a payload sample.
* **Learns** from your decision: **Benign** teaches the engine the pattern is safe and matching traffic stops being flagged; **Malicious** confirms the detection. Nothing changes in enforcement until you apply a verdict.
### Steps
1. Go to **Check Point WAF > Policy > Assets**, open your asset, and select the **Learn** tab. The badge shows how many items await your decision.
2. Pick a suggestion. Each card shows its grouping, the indicators found, a severity bar, and links to the events, **View Logs**, and **Tuning Advisor**.
3. Click **Tuning Advisor**.
4. Review the **Recommendation Verdict**, **Reason**, and **Sample**. Check the sample against what you know about your application — is this a path it legitimately uses?
5. Click **Apply verdict** to accept, or **Cancel** to decide later.
Allow up to **2 hours** for an applied verdict to reach the enforcing WAF agents.
### Notes
* A verdict applies to that specific URI or source — not to a broad URL or IP pattern. To allow a whole pattern, use an exception.
* Applying **Benign** to genuinely malicious traffic reduces protection for that pattern. If the sample doesn't clearly match something your application does, use **View Logs** to investigate first.
* The recommendation is based on observed traffic, not on your application's business logic. You are the tiebreaker on anything ambiguous.
---
# 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 dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://waf-doc.inext.checkpoint.com/how-to/use-automatic-tuning-suggestions.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.