Internal Agents Map

Scruff

Scruff investigates security alerts for Notion’s Detection and Response team, preparing analysis for human decisions.

Company
Notion
Approach type
Agent
Human involvement
Drafts reviewed
Invocation
Event-driven
Deployment stage
Deployed
Evidence strength
Detailed primary
Entry reviewed
Copy as MDAsk ChatGPT

How it works

security alert → investigation for DART decision.

Trigger investigation

An alert enters a structured Notion database.[Source 1]

Gather and correlate

Scruff follows the matching runbook and queries security sources through MCP.[Source 1]

Return findings

DART reviews the investigation and decides whether to declare an incident or dismiss the alert.[Source 1]

Where people stay involved

People review, approve, or guide the agent’s work here.

  • Supervision level

    Work-product review

    A person reviews the draft or implementation.

    Level 3 of 5

    • security alert → investigation for DART decision[Source 1]

How supervision levels work

Implementation details

Model
Not reported
Harness
Notion Custom Agents.[Source 1]
Sandbox
Not reported
Tool access
MCP connections to external security tools.[Source 1]
Knowledge
Runbooks stored as Notion pages.[Source 1]
Context management
A notes page retains lessons and accepts human edits.[Source 1]
Credentials
Not reported
Interfaces
Not reported

Validation and failure handling

Not reported: The available sources do not describe how the team checks the output.

Reported observations

These results come from the sources. Notes below each result explain what it covers and any reported limits.

Key observation

Notion reports more than six hours saved per week across DART.[Source 1]

Reported by
Notion
Scope
Scruff: Notion reports more than six hours saved per week across DART.

The source does not report the denominator of this figure.

About this result
Category
Adoption output
Evidence type
Reported measurement
What it covers
Scruff: Notion reports more than six hours saved per week across DART.

Lessons

Not reported: The available sources do not report lessons from this work.

Back to agents
Improve this record

Give your coding agent the context and instructions to prepare a source-backed update.

Paste the prompt into your coding agent, then describe the correction or add a public source.

Preview prompt

Sources and research details

Citations link to the original publisher. Each source also keeps a preserved copy in the repository, so a changed or removed page stays checkable.

  1. Meet Scruff, Security’s New AI Teammatehttps://www.notion.com/blog/meet-scruff-securitys-new-ai-teammateEngineering blog · First party · Last source verification: 2026-09-17
Question coverage and scope
purpose
Reported
workflow
Reported
human involvement
Reported
implementation
Reported
validation
Not reported
observations
Reported
lessons
Not reported
Research details for every claim on this page
  1. Summary
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Not assessed
    Confidence reason
    No explicit confidence assessment is recorded for this claim.
  2. Harness
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Not assessed
    Confidence reason
    No explicit confidence assessment is recorded for this claim.
  3. Knowledge
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Not assessed
    Confidence reason
    No explicit confidence assessment is recorded for this claim.
  4. Context management
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Not assessed
    Confidence reason
    No explicit confidence assessment is recorded for this claim.
  5. Tool access
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Not assessed
    Confidence reason
    No explicit confidence assessment is recorded for this claim.
  6. Trigger investigation
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Not assessed
    Confidence reason
    No explicit confidence assessment is recorded for this claim.
  7. Gather and correlate
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Not assessed
    Confidence reason
    No explicit confidence assessment is recorded for this claim.
  8. Return findings
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Not assessed
    Confidence reason
    No explicit confidence assessment is recorded for this claim.
  9. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    Self-reported by the source; no independent verification.
    Reported by
    Notion
    Scope
    Scruff: Notion reports more than six hours saved per week across DART.
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  10. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The source explicitly places the incident/false-positive decision with DART after Scruff gathers and analyzes evidence.
    Observation date
    2026-01-12