Skip to content

[K9VULN-16251] Add agentic Bits AI docs #37511

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
colemaring wants to merge 1 commit into
base: master
Choose a base branch
from
+6 −0
Open

[K9VULN-16251] Add agentic Bits AI docs #37511

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions content/en/security/code_security/static_analysis/ai_enhanced_sast.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,6 +143,12 @@ To narrow down your initial list for triage, in [Vulnerabilities][6], select **F
Each finding includes a section with an explanation of the assessment. You can provide Bits AI with feedback on its assessment using a thumbs up 👍 or thumbs down 👎.
{{< img src="/code_security/static_analysis/false_positive_filtering_sast_side_panel_higher_res_png.png" alt="Visual indicator of a false positive assessment in SAST side panel" style="width:100%;">}}

### Agentic Bits AI assessments

For supported SAST rules, Bits AI Assessments use an agentic approach to gather repository context before classifying findings. Bits AI can read related files and search for symbols and patterns. It can also inspect nearby directory structure to verify definitions, call paths, sanitizers, and framework wiring that are not visible in a single file.

@domalessi domalessi Jun 15, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
For supported SAST rules, Bits AI Assessments use an agentic approach to gather repository context before classifying findings. Bits AI can read related files and search for symbols and patterns. It can also inspect nearby directory structure to verify definitions, call paths, sanitizers, and framework wiring that are not visible in a single file.
For supported SAST rules, Bits AI Assessments use an agentic approach to gather repository context before classifying findings. Bits AI can read related files and search for symbols and patterns. Bits AI can also inspect the surrounding directory structure to verify definitions, call paths, sanitizers, and framework wiring that are not visible in a single file.

@domalessi domalessi Jun 15, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Capitalization of "assessments" is inconsistent. The heading (line 146) uses lowercase "assessments" (correct sentence case), but the body capitalizes it as "Assessments." If "Bits AI Assessments" is an official feature name, it should be capitalized throughout.


This extra context helps Bits AI distinguish true positives from false positives for findings that depend on cross-file behavior. Agentic Bits AI Assessments apply to SAST findings only.

@domalessi domalessi Jun 15, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
This extra context helps Bits AI distinguish true positives from false positives for findings that depend on cross-file behavior. Agentic Bits AI Assessments apply to SAST findings only.
The additional repository context helps Bits AI distinguish true positives from false positives for findings that depend on cross-file behavior. Agentic Bits AI Assessments apply to SAST findings only.


## Remediation

Datadog SAST uses the [Bits Code][10] to generate code fixes for vulnerabilities. You can remediate individual vulnerabilities or fix multiple vulnerabilities using bulk remediation campaigns.
Expand Down
Loading