Docs

Appearance

Control Assessment Agent ​

The Control Assessment Agent produces a structured draft assessment for a control, grounded in the control definition and the evidence linked to it. It helps teams run consistent readiness conversations without turning every review into a blank page.

What this is ​

When you run the agent, it generates:

  • a readiness score from 0 to 100
  • a short summary of what the current evidence does and does not support
  • gaps with analysis and evidence references
  • recommendations with evidence references
  • a list of evidence sources used

The output is a draft. Humans remain accountable for what gets accepted, edited, and saved.

Where in Modulos ​

You run the Control Assessment Agent from the control detail view.

  • Project → Controls → select a control → Assessment to run the agent and review output
  • Project → Controls → select a control → Assessment → Save Assessment to store the assessment as part of the audit trail
Control Assessment tab showing a readiness score, evidence sources, gaps, and the AI Agent and Save Assessment actions.
The Assessment tab shows the agent output as a structured readiness draft you can save into the audit trail. UI shown in dark mode.
  1. 1
    AI Agent
    Generate or refresh the assessment draft from the control definition and linked evidence.
  2. 2
    Save Assessment
    Persist the draft as a saved assessment record for review and audit.
  3. 3
    Readiness score and summary
    A structured snapshot of how well the control is supported by current evidence.
  4. 4
    Sources
    The evidence items the agent used as inputs.
  5. 5
    Gaps
    Where evidence is missing, insufficient, or misaligned, with references back to sources.

Who can do what ​

Permissions

You need project permissions to run the agent and to save assessments.

  • Project owners and editors typically run the agent, review the draft, and save the assessment.
  • Reviewers and auditors typically read saved assessments and follow evidence references back to artifacts.

If you don’t see the AI Agent button or the Assessment tab, ask your project owner or organization admin.

How it works ​

When you run the agent, Modulos:

  1. takes the control’s question, description, and guidance
  2. finds the evidence linked to the control
  3. searches within that evidence for relevant passages
  4. generates a structured assessment in the project language

Evidence references in gaps and recommendations point back to the underlying artifacts, so reviewers can verify the basis.

How to use it ​

  1. Attach the most relevant evidence to the control.
  2. Open the control’s Assessment tab and select AI Agent.
  3. Read the summary, then review gaps and recommendations.
  4. Update evidence and control report content as needed, then re-run the agent.
  5. When the draft matches your judgement, select Save Assessment.

Important considerations ​

  • The readiness score is not a certification. Use it to focus review effort, not as an approval decision by itself.
  • If evidence is missing, the agent will correctly report gaps. Treat this as a checklist to collect the right artifacts.
  • Run assessments early and re-run when evidence changes. Controls become harder to change once executed.
  • AI can make mistakes. Validate claims and references against the underlying evidence.