Paste one of these into your AI coding agent to build the entire system

Prerequisites

Docker Desktop Python 3.11+ Node.js 20+ Git Ollama

Docker for Qdrant/n8n containers · Ollama for local embeddings · Python for MCP server/governance/dashboard · Node.js for plugins/hooks/MCP

Claude Code
Read all 19 PRDs at https://bulletproofsoftware.ai/code/prds/ using WebFetch. Then build all nineteen systems in dependency order: (1) Plugin ecosystem with two-layer hook architecture, (2) Context guard plugin, (3) Persistent vector memory with Qdrant + Ollama + 60 MCP tools + 32 n8n workflows, (4) Agent governance framework with constitutional layer, (5) Multi-agent orchestration with 38 agents, Gemini validation, and 2,046-line state schema, (6) Memory visualization dashboard, (7) Markdown-for-agents proxy, (8) Code assurance platform, (9) Agentic data plane with DAG lineage and PII classification, (10) Agent economics with cost tracking and model routing, (11) Runtime security with behavioral monitoring and guardian agents, (12) Self-healing workflow recovery with 7-category failure classification, (13) Event-driven automation with 10-category taxonomy and 32 n8n workflows, (14) Process knowledge base with structured business rules and 3 MCP query tools, (15) Outcome measurement with 8 metrics and value attribution, (16) Predictive scaling with workload prediction and adaptive model routing, (18) A2A agent interoperability gateway with REST, MCP Bridge, and A2A protocol adapters, (19) Compliance portal with HITL interface for auditors, compliance officers, and data subject self-service. Wire hooks in both settings.json and plugin hooks.json. Use Docker Compose for infrastructure. All requirements are in the PRDs.
Gemini CLI
Fetch all 19 PRDs from https://bulletproofsoftware.ai/code/prds/. Build all nineteen systems in dependency order following each PRD's requirements. Adapt the plugin architecture for GEMINI.md configuration and Gemini's extension model. Use the same Docker Compose stack (Qdrant, PostgreSQL, n8n, Ollama). Implementation order: plugins → context guard → memory (60 MCP tools) → governance → orchestration (38 agents) → dashboard → markdown proxy → code assurance → data plane → agent economics → runtime security → self-healing workflows → event-driven automation → process knowledge base → outcome measurement → predictive scaling → A2A agent interoperability → compliance portal.
Codex CLI
Fetch all 19 PRDs from https://bulletproofsoftware.ai/code/prds/. Build all nineteen systems following each PRD's requirements. Adapt the plugin architecture for AGENTS.md configuration and Codex's event model. Use Docker Compose for Qdrant, PostgreSQL, n8n, and Ollama. Build order: plugins → context guard → memory system → governance → orchestration → dashboard → markdown proxy → code assurance → data plane → agent economics → runtime security → self-healing workflows → event-driven automation → process knowledge base → outcome measurement → predictive scaling → A2A agent interoperability → compliance portal.

Nineteen Architectural Domains

Plugin Ecosystem

Two-layer hook architecture, skills, agents, commands, MCP integration

12 requirements

Multi-Agent Orchestration

38 agents, 2,046-line state schema, Gemini validation, tiered quality gates

19 requirements

Context Management

4-tier escalation, velocity prediction, auto-memory, 5-compartment budget

12 requirements

Persistent Vector Memory

60 MCP tools, 7+ collections, 32 n8n workflows, constitutional governance

18 requirements

Agent Governance

Identity manifests, 3-tier tool classification, constitutional contracts, audit bus

18 requirements

Memory Dashboard

FastAPI + HTMX, D3.js knowledge graphs, Chart.js analytics

12 requirements

Markdown-for-Agents

HTML-to-markdown proxy with Playwright fallback for JS-rendered pages

12 requirements

Code Assurance Platform

37 tools, 12 scan profiles, 6-stage enrichment, 1000-point scoring

20 requirements

Agentic Data Plane

Data lineage, quality validation, pipeline observability, continuous classification, financial reconciliation

24 requirements

Agent Economics & Cost Governance

Per-agent cost tracking, budget caps, model routing, token optimization

14 requirements

Agent Runtime Security & Identity

Behavioral monitoring, identity lifecycle, memory integrity, guardian agents

18 requirements

Self-Healing Workflows

Automated failure recovery with 7-category classification, strategy playbook, checkpoint-aware restart

14 requirements

Event-Driven Automation

Centralized event taxonomy, YAML routing rules, n8n workflow registry with 32 workflows formalized

14 requirements

Process Knowledge Base

Structured business rules, decision trees, SOPs, and edge-case catalogs for agent decision points

14 requirements

Outcome Measurement

Value tracking beyond cost — task completion rates, TTR, quality trending, ROI attribution

14 requirements

Predictive Scaling

Workload prediction, adaptive model routing, cache pre-warming, cost forecasting

12 requirements

A2A Agent Interoperability

External agent gateway with REST, MCP Bridge, and A2A protocol adapters for cross-platform orchestration

16 requirements

Regulatory Compliance & Audit Trail

Human attribution, cryptographic audit chain, evidence packages, model cards — NAIC / SOX / GDPR / NY DFS Part 500 defensibility

50 requirements

Compliance Portal & HITL Interface

Web portal for compliance officers, auditors, data subjects, domain experts — audit explorer, evidence packages, gate decisions, DSR management, regulatory reports

39 requirements

These are blueprints, not downloads. Every development environment is different. Give the PRDs to your AI coding agent and it generates an implementation tailored to your infrastructure, your tools, your constraints.