Ctrlk
Changelog NotificationsAPIAikido login
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Ask Aikido

Ask Aikido is the conversational interface to Aikido Agent on a specific finding.

Ask Aikido is how you talk to Aikido Agent on a specific finding. Use it when you want to validate a triage decision, inspect the real attack path, or adapt a generated fix, without leaving Aikido or pasting findings into a separate chatbot.

Aikido Agent already filters noise automatically through SAST AutoTriage, Secrets AutoTriage, and CVE Exploitability Analysis. Most of the time, that is enough. Use Ask Aikido when you want to dig deeper.

Use cases

1. SAST: Code analysis

Ask questions like Is this actually risky for us?, Why did AutoTriage raise the severity for this issue?, or Walk me through how this could be exploited in practice.

Use this chat to:

  • validate severity

  • understand the realistic attack path

  • decide whether to fix now, schedule it, or ignore it with a reason

Open View Code Analysis in the sidebar for a SAST issue, then click Ask Aikido in the top left.

2. Dependencies: Full impact analysis

Ask questions like Is this actually reachable in our app? or Explain the full impact analysis.

Use this chat to turn dependency paths and call graph output into plain-language exploitability guidance.

Open View Reachability Analysis in the sidebar for a dependency issue, then click Ask Aikido in the bottom left.

3. Refine AutoFix

Use this chat when an AutoFix is close, but not ready to merge. Ask questions like Can you adjust this patch to X, Explain the reasoning for this fix, or Please add a comment explaining the fix.

You can ask Aikido Agent to:

  • match your naming and style conventions

  • add tests or small logic changes

  • adapt the patch to your architecture

For more on fix refinement, see Refine AutoFixes with Aikido AI.

What it knows

Each chat runs with full context: the finding, affected code, CVE metadata, reachability signals, and the diff (where relevant). Answers are grounded in your specific stack, not generic security advice.

Actions you can take from chat

From the chat, you can:

  • ignore the issue with AI-generated reasoning

  • create or refine an AutoFix

  • save custom context to improve future suggestions

Related pages

Last updated

Was this helpful?