> For the complete documentation index, see [llms.txt](https://docs.konvu.com/konvu/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.konvu.com/konvu/triage-and-remediation/exploitability-assessment/answering-konvus-questions.md).
# Answering Konvu's Questions
When an assessment result is Needs input, Konvu has questions that could change the result. Here's how to answer them.
When an assessment result is **Needs input**, Konvu has identified specific questions about your environment that could determine whether a vulnerability is exploitable or a false positive. Your answers provide the missing context Konvu needs to reach a definitive assessment result.
## Where questions appear
Konvu's questions surface in two places:
1. A dedicated view (accessible from the top navigation) that lists all pending questions across your findings. This is the most efficient way to work through questions.
2. **The finding detail page.** Each finding with a Needs input result shows its pending questions inline within the assessment timeline.
The Inbox groups questions by repository, so you can work through related questions together.
## How deduplication works
Konvu often needs the same information for multiple findings. For example, if 12 findings in the same repository all depend on knowing whether your application accepts untrusted XML input, Konvu groups them into a single question.
When you answer a deduplicated question:
* Your answer applies to **all affected findings** at once.
* Each of those findings is reassessed with your input.
* You can see the number of affected findings next to each question in the Inbox.
*Example: Konvu asks "Does your application process untrusted XML input?" This question affects 8 findings across `CVE-2024-34750`, `CVE-2024-24549`, and others in your `backend-api` repository. You answer once, and all 8 findings are reassessed.*
## Answering questions
Each question includes:
* **The question itself.** A specific, actionable question about your environment or code.
* **A suggested command** (when applicable). A terminal command you can run to find the answer. Copy it directly from the UI.
* **Context.** Expand "Why is this needed?" to see why the answer matters for the assessment.
To answer a question:
1. Read the question and (if needed) run the suggested command or check your code.
2. Type your answer in the text field. Be specific. "Yes, we use Spring Boot's default Jackson configuration" is more useful than "Yes."
3. Press Enter or click the submit button.
### Auto-reply for similar questions
When answering, a checkbox labeled **"Auto-reply similar questions"** is enabled by default. When checked, Konvu applies your answer to other questions that ask the same thing for different findings. This prevents you from answering the same question repeatedly.
If a question is specific to a single finding and shouldn't be generalized, uncheck this option before submitting.
### Batch answering from the Inbox
The Inbox supports selecting multiple questions and answering them together:
1. Select questions using the checkboxes (or click a question row to select its group).
2. A batch answer panel appears at the bottom of the screen.
3. Type your answer. It will apply to all selected questions.
4. Submit with the button or Cmd+Enter (Ctrl+Enter on Windows/Linux).
This is useful when several questions have the same answer, for instance, confirming that your application doesn't use a specific framework feature across multiple findings.
## What happens after you answer
After you submit an answer:
1. **Konvu interprets your input.** The system maps your free-text answer to a determination about the exploitability condition in question.
2. **A follow-up assessment runs.** The finding is reassessed with your input factored in.
3. **The assessment result may change.** A finding that was Needs input might become **False Positive** (your answer confirmed non-exploitability) or **Exploitable** (your answer confirmed exploitability). It might also remain **Needs input** if Konvu has additional questions.
You can see the status of follow-up assessments in the "Answered" tab of the Inbox. Each answered question shows whether the follow-up assessment is still running, and the assessment result once it completes.
## Editing and deleting answers
If you made a mistake or your environment changed:
* **Edit.** Click the pencil icon next to a clarified question on the finding detail page to update your answer.
* **Delete.** Click the trash icon to remove your answer entirely. This re-triggers the follow-up assessment without your input.
Deleting an answer that was auto-propagated to similar questions will also remove it from those findings.
{% hint style="info" %}
Answering Konvu's questions is the highest-leverage triage activity. A single answer can resolve dozens of findings at once through deduplication, turning Needs input results into definitive Exploitable or False Positive assessment results.
{% endhint %}
---
# 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.konvu.com/konvu/triage-and-remediation/exploitability-assessment/answering-konvus-questions.md?ask=&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.
