mancitrus/system-prompts-and-models-of-ai-tools
1
0
Fork 0
mirror of https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git synced 2026-06-18 07:19:35 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
f75e7c331e
system-prompts-and-models-o.../salesflow-saas/docs/governance/technology-radar-tier1.md
Claude a319feb6d7
feat(dealix): complete Tier-1 Sovereign Enterprise Growth OS 
Governance layer (14 docs):
- MASTER_OPERATING_PROMPT.md — operating constitution (five planes, six tracks, policy classes)
- docs/ai-operating-model.md — five-plane architecture (Decision/Execution/Trust/Data/Operating)
- docs/dealix-six-tracks.md — six strategic tracks (Revenue/Intelligence/Compliance/Expansion/Operations/Trust)
- docs/governance/execution-fabric.md — OpenClaw execution plane deep dive
- docs/governance/trust-fabric.md — trust plane with contradiction engine + evidence packs
- docs/governance/saudi-compliance-and-ai-governance.md — PDPL/ZATCA/SDAIA/NCA live controls
- docs/governance/technology-radar-tier1.md — Core/Strong/Pilot/Watch/Hold classification
- docs/governance/partnership-os.md — alliance lifecycle management
- docs/governance/ma-os.md — M&A corporate development lifecycle
- docs/governance/expansion-os.md — geographic and vertical growth
- docs/governance/pmi-os.md — post-merger integration framework
- docs/governance/executive-board-os.md — executive decision surfaces
- docs/execution-matrix-90d-tier1.md — 90-day sprint execution plan
- docs/adr/0001-tier1-execution-policy-spikes.md — 8 architectural decisions

Backend (3 models, 6 services, 8 API routes):
- Contradiction Engine — detect/track system conflicts
- Evidence Pack System — tamper-evident audit proof with SHA256
- Saudi Compliance Matrix — live PDPL/ZATCA/SDAIA/NCA controls
- Executive Room — unified executive decision surface
- Connector Governance — integration health monitoring
- Model Routing Dashboard — LLM provider metrics
- Forecast Control Center — actual vs forecast across tracks
- Approval Center — enhanced approval queue with SLA

Frontend (9 components):
- Executive Room, Evidence Pack Viewer, Approval Center
- Connector Governance Board, Saudi Compliance Dashboard
- Actual vs Forecast Dashboard, Risk Heatmap
- Policy Violations Board, Partner Pipeline Board

Tooling:
- scripts/architecture_brief.py — preflight validation (40/40 checks pass)
- Updated CLAUDE.md and AGENTS.md with governance references

https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
2026-04-16 12:48:13 +00:00

5.9 KiB
Raw Blame History

Technology Radar — Tier 1

Parent: MASTER_OPERATING_PROMPT.md
Plane: Operating | Tracks: Operations, Intelligence
Version: 1.0 | Status: Canonical

Overview

The Technology Radar classifies every technology Dealix uses or considers. Classification determines governance, investment, and documentation requirements.

Review cadence: Quarterly
Promotion/demotion: Requires ADR with evidence

Core — Production, Non-Negotiable

These technologies are in production and foundational. Removing any of them would require a major architectural decision.

Technology Version Purpose Plane
FastAPI 0.115.x Backend API framework Execution
SQLAlchemy 2.0.x Async ORM Data
PostgreSQL 16 Primary database Data
asyncpg 0.30.x Async PostgreSQL driver Data
pgvector 0.3.x Vector embeddings for RAG Data
Redis 7 Cache + task broker Data
Celery 5.x Async task queue Execution
Next.js 15.x Frontend framework Decision
TypeScript 5.7 Frontend type safety Decision
Tailwind CSS 3.4 Styling Decision
OpenClaw 2026.4.x Durable execution engine Execution
Groq 0.12.x Primary LLM (fast, Arabic) Intelligence
WhatsApp Cloud API - Primary communication channel Execution
Pydantic 2.10.x Data validation All
Alembic 1.14.x Database migrations Data
Docker Compose - Container orchestration Operating
GitHub Actions - CI/CD Operating
JWT (PyJWT) - Authentication Trust
StructLog 24.x Structured logging Operating
pytest - Testing framework Operating

Strong — Validated, Deploying or Near-Ready

These have been validated and are either deployed or actively being integrated.

Technology Version Purpose Plane Evidence
Claude Opus 4.6 Strategic LLM (via model_router) Intelligence Configured in model_router.py
OpenAI 2.8.x Fallback LLM Intelligence Configured as fallback
Salesforce Agentforce - CRM sync Data Plugin exists in openclaw/plugins/
Stripe - Payment processing Execution Plugin + service exist
LiteLLM 1.74.x Multi-provider abstraction Intelligence In requirements.txt
Instructor 1.14.x Structured LLM outputs Intelligence In requirements.txt
LangChain - Chain orchestration Execution In requirements.txt
LangGraph 0.2.x Workflow graphs Execution In requirements.txt
CrewAI - Multi-agent coordination Execution In requirements.txt
Mem0 - Agent long-term memory Data In requirements.txt
Sentry 2.x Error tracking Operating In requirements.txt
Prometheus - Metrics Operating In requirements.txt
CAMEL-Tools 1.5.x Arabic NLP Intelligence In requirements.txt
WeasyPrint 60.x PDF generation (Arabic RTL) Execution In requirements.txt
Playwright - E2E testing Operating In frontend package.json

Pilot — Experimenting, Behind Feature Flags

These are being tested but not committed to. Usage is limited and behind feature flags.

Technology Purpose Plane Notes
Voice Agents (Twilio) Voice call integration Execution Plugin exists, limited testing
Contract Intelligence Contract analysis Intelligence Plugin exists, early stage
Gemini Alternative LLM routing Intelligence In model_router config
DeepSeek Coding assistance routing Intelligence In model_router config
DocuSign/Adobe Sign E-signatures Execution Env vars defined, not live
cal.com Meeting booking Execution Integration path defined

Watch — Evaluating, No Code Yet

These are being evaluated for future adoption. No production code exists.

Technology Purpose Evaluation Criteria
Temporal Long-running durable workflows Compare vs OpenClaw durable_flow
OPA Policy engine Compare vs openclaw/policy.py
OpenFGA Authorization graph Compare vs RBAC + tenant isolation
Vault Secrets management Compare vs env vars
Keycloak Identity provider Compare vs JWT auth
Gong Revenue intelligence API integration feasibility
Apollo Lead enrichment Data quality evaluation
HubSpot CRM alternative Env var defined, not active

Hold — Explicitly Not Adopting

These have been evaluated and rejected for Dealix.

Technology Reason for Rejection
External RAG SaaS (Onyx, etc.) Policy: PostgreSQL + pgvector + KnowledgeService only
Schema-per-tenant Unnecessary complexity; row-level isolation sufficient
GraphQL REST + structured outputs adequate; GraphQL adds complexity
MongoDB PostgreSQL covers all use cases including JSON (JSONB)
Firebase Not suitable for Saudi data residency requirements
Supabase PostgreSQL self-hosted preferred for control

Governance Rules

  1. No technology enters Core without 90 days in Strong and a passing ADR.
  2. No technology enters Strong without a Pilot demonstrating value.
  3. Pilot technologies must have feature flags and can be disabled without downtime.
  4. Watch technologies have no code — only evaluation documents.
  5. Hold decisions are permanent unless a new ADR overturns them with evidence.
  6. pgvector security patches must be applied within 7 days of release.
  7. LLM provider diversity is maintained — never depend on a single provider.