Entry Modes

Capture Mode

Use capture mode when starting a Responsible AI assessment from scratch with no prior artifacts. The agent conducts a full interview about the AI system, building understanding from the ground up.

How It Works

1. Provide an optional project slug or let the agent derive one from your project name
2. The agent resolves attached-material pointers and output preferences
3. The agent creates .copilot-tracking/rai-plans/{project-slug}/ and initializes state.json with entryMode: "capture" and currentPhase: 1, then enters the Phase 1 preflight
4. After preflight and reference discovery, Phase 1 begins with up to 7 questions covering: AI system purpose, technology stack, model types, stakeholder roles, data inputs and outputs, deployment model, and intended use context
5. Answer questions conversationally; use "skip" or "n/a" for items that do not apply
6. The agent summarizes findings and asks for confirmation before advancing to Phase 2

To start capture mode, select the RAI Planner agent and describe the AI system you want to assess.

When to Choose Capture Mode

Signal	Recommendation
No PRD, BRD, or security plan exists	Use capture mode
Exploring whether an AI system needs RAI assessment	Use capture mode
Standalone AI project without broader security context	Use capture mode
Rapid prototyping with an evolving scope	Use capture mode

From-PRD Mode

Use from-prd mode when product requirements documents or business requirements documents already exist in .copilot-tracking/. The agent extracts AI system scope, stakeholders, and technology stack from these artifacts, reducing the Phase 1 interview to confirmation and gap-filling.

How It Works

1. The agent resolves the PRD pointer and output preferences; when you do not name a PRD, it lists candidates from .copilot-tracking/prd-sessions/ and .copilot-tracking/brd-sessions/ for you to confirm
2. The agent creates .copilot-tracking/rai-plans/{project-slug}/ and initializes state.json with entryMode: "from-prd" and currentPhase: 1, then enters the Phase 1 preflight
3. During project-material discovery in the preflight, the agent reads the PRD and extracts AI system scope, technology stack, model types, deployment model, and stakeholders
4. Phase 1 begins with pre-populated fields; the agent asks clarifying questions targeting gaps in the extracted information

To start from-prd mode, select the RAI Planner agent and ask it to start from your product or business requirements, optionally naming the PRD. When no requirements artifact is found, the agent offers to switch to capture mode.

When to Choose From-PRD Mode

Signal	Recommendation
PRD or BRD artifacts exist in .copilot-tracking/	Use from-prd mode
Product requirements are well-documented but no security plan exists	Use from-prd mode
Multiple stakeholders contributed to product definition	Use from-prd mode to leverage that work

From-Security-Plan Mode

Use from-security-plan mode after completing a security plan with the Security Planner. This is the recommended entry mode for most assessments because it inherits AI component data, continues threat ID sequences, and provides the richest starting context.

How It Works

1. The agent validates the security-plan pointer and resolves output preferences; when you do not name a plan, it lists the Security Planner projects it finds under .copilot-tracking/security-plans/ and asks you to choose
2. The agent creates .copilot-tracking/rai-plans/{project-slug}/ and initializes state.json with entryMode: "from-security-plan" and currentPhase: 1, then enters the Phase 1 preflight
3. During project-material discovery in the preflight, the agent reads the security plan state.json and extracts AI components from its aiComponents array
4. Threat IDs start at the next sequence after the security plan's threat count, maintaining continuity across both assessments
5. Phase 1 begins with pre-populated AI element inventory; the agent asks targeted questions about RAI-specific aspects not covered in the security plan

To start from-security-plan mode, select the RAI Planner agent and ask it to start from your completed security plan, or choose the RAI Planner handoff at the end of a Security Planner session. When no security plan exists, the agent offers to switch to capture mode.

When to Choose From-Security-Plan Mode

Signal	Recommendation
Security Planner has completed with raiEnabled: true	Use from-security-plan mode
The security plan identified AI or ML components	Use from-security-plan mode
You want threat ID continuity across security and RAI assessments	Use from-security-plan mode

NOTE

The Security Planner recommends this entry mode during its Phase 6 handoff when raiEnabled is true. The RAI Planner reads security plan artifacts as read-only and never modifies files under .copilot-tracking/security-plans/.

Comparing Entry Modes

Aspect	Capture	From-PRD	From-Security-Plan
Initial context	None	Product requirements	Security plan with AI components
AI component discovery	Manual via interview	Extracted from PRD artifacts	Pre-populated from security plan
Threat ID continuity	Starts at T-RAI-001	Starts at T-RAI-001	Continues from security plan count
Time to Phase 2	Longest	Medium	Shortest
Best for	Fresh assessments, exploratory	Projects with product docs	Recommended post-security-plan

After Choosing a Mode

Once Phase 1 completes, all three modes converge into the same workflow for Phases 2 through 6. The entry mode is recorded in state.json and cannot change after assessment begins.

See Phase Reference for the complete specification of each phase.

🤖 Crafted with precision by ✨Copilot following brilliant human instruction, then carefully refined by our team of discerning human reviewers.