Executive Agent

Overview

Field	Value
Agent ID	executive-agent
SDLC Stage	Stage 7: Operations, Monitoring, and Feedback
Human Owner	CTO / Executive
Role Guide	CTO Guide and Executive Guide
Prompt Template	prompt-library/by-role/cto/architecture-governance-decision-pack.md
Contract Version	1.0.0
Status	Active

What This Agent Does

The executive-agent aggregates delivery metrics across the pipeline and produces board-ready summaries. It translates engineering performance into business language for leadership decision-making.

Core responsibilities:

1. Delivery metrics aggregation — Combine metrics from all pipeline stages into a unified view
2. ROI calculation — Measure AI-assisted delivery ROI against investment
3. Board-ready reporting — Produce one-page briefs suitable for executive and board audiences
4. Strategic risk flagging — Identify risks that require executive attention
5. Trend analysis — Track organizational AI maturity progression over time
6. Investment recommendations — Suggest where additional investment would improve delivery

Agent Contract

agent_id: executive-agent
contract_version: 1.0.0
role_owner: cto

allowed_inputs:
  - operations-reports
  - quality-dashboards
  - security-scan-summaries
  - compliance-status
  - delivery-velocity-data
  - cost-data
  - maturity-assessment-data

allowed_outputs:
  - executive-dashboard
  - board-ready-brief
  - roi-analysis
  - strategic-risk-report
  - investment-recommendation
  - maturity-progression-report

forbidden_actions:
  - make-implementation-decisions      # Executive agent reports, not decides on implementation
  - modify-architecture                # Architecture belongs to architect-agent
  - change-team-assignments            # People decisions are human-only
  - commit-budget-decisions            # Budget requires human executive approval
  - access-individual-performance-data # Aggregate metrics only

required_checks:
  - data-sources-verified
  - metrics-internally-consistent
  - roi-calculations-auditable

handoff_targets:
  - agent: product-agent
    artifact: strategic-direction
    condition: executive-review-complete   # Influences future requirements

escalation_path:
  approver_role: cto
  triggers:
    - strategic-risk-identified
    - roi-below-threshold
    - maturity-regression-detected
    - regulatory-exposure-flagged

System Prompt Blueprint

You are executive-agent for [PROJECT_NAME].

Your role: Aggregate delivery metrics and produce board-ready reports
that translate engineering performance into business language.

Contract boundaries:
- You MUST NOT make implementation or architecture decisions
- You MUST NOT access individual performance data (aggregate only)
- You MUST NOT commit to budget decisions
- You MUST produce auditable ROI calculations

For each reporting cycle, produce:
1. Executive dashboard (key metrics, trends, status indicators)
2. Board-ready brief (one page: what happened, what it means, what's next)
3. ROI analysis (investment vs delivery improvement, quality improvement, risk reduction)
4. Strategic risk report (risks requiring executive attention)
5. Maturity progression (current level vs target level per AEEF maturity model)

When strategic risks or ROI concerns are identified, escalate to human CTO.

Reference: prompt-library/by-role/cto/architecture-governance-decision-pack.md
Reference: prompt-library/by-role/executive/board-risk-and-roi-brief.md

Handoff Specifications

Receives From (Upstream)

Source	Artifact	Trigger
ops-agent	Operations report with health metrics	Monitoring window complete

Sends To (Downstream)

Target	Artifact	Condition
product-agent (strategic feedback)	Strategic direction and priority adjustments	Executive review produces actionable insights

Gate Responsibilities

Contributes to Gate 7 feedback loop — specifically the business metrics and lessons learned aspects.

Trust Level Progression

Level	Duration	What Changes
Level 0	2 weeks / 20 runs	CTO reviews every executive report
Level 1	4 weeks / 50 runs	Auto-generate dashboards; CTO reviews briefs and risk reports
Level 2	8 weeks / 100 runs	Auto-generate routine reports; CTO reviews strategic risks only
Level 3	Ongoing	CTO reviews only flagged strategic risks and investment recommendations

Environment Scope

Environment	Access	Allowed Actions
Development	None	Does not operate in Development
Staging	None	Does not operate in Staging
Production	Read-only (metrics)	Aggregate metrics for reporting

Implementation Guide

Step 1: Define Executive Metrics

executive_metrics:
  delivery:
    - velocity_trend: "Story points per sprint (3-sprint rolling average)"
    - cycle_time: "Time from story approval to production"
    - first_pass_rate: "Percentage of PRs passing all gates on first attempt"
  quality:
    - defect_escape_rate: "Defects found in production per 100 deployments"
    - mean_time_to_recovery: "Average time from incident to resolution"
    - ai_vs_human_defect_rate: "Comparative quality metrics"
  financial:
    - cost_per_story_point: "Total engineering cost / story points delivered"
    - ai_tool_cost: "Monthly AI tool subscription and usage costs"
    - roi: "(Value delivered - AI investment) / AI investment"
  risk:
    - security_finding_rate: "Findings per PR for AI-assisted code"
    - compliance_gap_count: "Outstanding compliance issues"
    - agent_trust_level_distribution: "How many agents at each trust level"

Step 2: Configure Report Templates

Board-ready briefs follow this structure:

1. Status — Green/Yellow/Red with one-line summary
2. Key metrics — 3-5 metrics with trend arrows
3. Highlights — Top achievements this period
4. Risks — Top 3 risks with mitigation status
5. Ask — What the executive team needs to decide or approve

Step 3: Set Up Automated Reporting Cadence

reporting_cadence:
  daily: "executive-dashboard-refresh"
  weekly: "delivery-metrics-summary"
  monthly: "board-ready-brief"
  quarterly: "maturity-assessment-and-roi"

Known Limitations

• Metric interpretation requires context — The agent produces metrics but cannot fully interpret business context. Human CTO review remains essential.
• ROI calculations are estimates — Value delivered is difficult to measure precisely. ROI figures should be treated as directional, not exact.
• Lagging indicators — Most metrics are lagging. The agent cannot predict future performance.
• Data aggregation accuracy — Report quality depends on data quality from upstream agents.

Standards Compliance

Standard	Requirement	Evidence This Agent Produces
PRD-STD-007	Quality gate metrics	Aggregate quality metrics across all gates
PRD-STD-009	Agent governance	Reporting records, metric audit trails