Skip to content

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

Open
colemaring wants to merge 1 commit into
masterfrom
cole.maring/agentic-bits-ai-assessments-docs
Open

[K9VULN-16251] Add agentic Bits AI docs#37511
colemaring wants to merge 1 commit into
masterfrom
cole.maring/agentic-bits-ai-assessments-docs

Conversation

@colemaring

@colemaring colemaring commented Jun 15, 2026

Copy link
Copy Markdown
Contributor

What does this PR do? What is the motivation?

Adds a short agentic Bits AI assessments section to AI Enhanced Static Code Analysis.

Related release note PR
https://github.com/DataDog/web-ui/pull/319445

@github-actions

Copy link
Copy Markdown
Contributor

Preview links (active after the build_preview check completes)

Modified Files

@colemaring colemaring marked this pull request as ready for review June 15, 2026 20:13
@colemaring colemaring requested a review from a team as a code owner June 15, 2026 20:13
@domalessi domalessi self-assigned this Jun 15, 2026

@domalessi domalessi left a comment

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.

A few minor suggestions. Hit me up when ready for a final look!


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.

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.

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.


### 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.

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.


### 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.

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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants