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 2026-06-17 23:09:35 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
47f4dc2fb6
system-prompts-and-models-o.../dealix/docs/PRIVATE_BETA_LAUNCH_TODAY.md
Dealix Builder bcf545c22e feat(self-improving): Hermes-inspired Agent Platform — 6 layers + 30 endpoints + 76 tests + Private Beta launch 
Security Curator (4 modules) — جدار الحماية الأول
- secret_redactor: 11 patterns (GitHub PAT, OpenAI/Anthropic/Supabase/WhatsApp/Moyasar/Sentry/Google/AWS/private keys); never returns raw secret
- patch_firewall: blocks .env / credentials.json / RSA keys; scans added lines for secret patterns
- trace_redactor: masks phones (+966...) and emails for PII safety
- tool_output_sanitizer: cleans tool outputs before they hit ledger/Proof Pack/UI/observability

Growth Curator (5 modules) — التحسين الذاتي
- message_curator: grades Arabic messages (0..100), detects 8 risky phrases, suggests Saudi-tone skeleton
- playbook_curator: scores playbooks by outcome (accept/reply/meeting/deal); winner/promising/needs_work/archive
- mission_curator: scores completed missions; ship_it_widely/iterate/rework_or_retire
- skill_inventory: deterministic 23-skill catalog across 5 layers
- curator_report: weekly Arabic summary "ماذا تعلمنا هذا الأسبوع"

Meeting Intelligence (5 modules) — ذكاء الاجتماعات
- transcript_parser: accepts Google Meet entries OR plain "Speaker: text" format
- meeting_brief: 6-section pre-meeting brief in Arabic (objective/questions/objections/offer/next-step)
- objection_extractor: 8 categories (price/timing/authority/trust/integration/competitor/results/complexity)
- followup_builder: email + WhatsApp drafts; live_send_allowed=False always
- deal_risk: 0..100 score from objections + missing next-step + decision-maker absence + days-since-touch

Model Router (5 modules) — موجّه النماذج
- provider_registry: 7 providers (Claude Sonnet/Haiku, GPT-4-class, GPT-4o-mini, Gemini Pro, Azure OAI KSA-region, Local Qwen Arabic-tuned)
- task_router: 10 task types × routing decisions with reasons_ar
- cost_policy: bulk → low; output > 1500 tokens → high
- fallback_policy: high-sensitivity workloads prefer KSA-region/self-hosted FIRST
- usage_dashboard: deterministic demo of all task routes

Connector Catalog (3 modules) — كتالوج التكاملات
- 14 connectors (WhatsApp Cloud, Gmail, Calendar, Google Meet, Moyasar, LinkedIn Lead Forms, Google Business Profile, X API, Instagram, Sheets, CRM, Website Forms, Composio, MCP Gateway)
- Each has launch_phase (1-4), risk_level, allowed_actions, blocked_actions, Arabic risk dossier
- WhatsApp blocks cold_send_without_consent; Moyasar blocks store_card_number; MCP requires allowlist

Agent Observability (5 modules) — مراقبة الوكلاء + التقييمات
- trace_events: SHA256-hashes user/company IDs; sanitizes payload/output before logging
- safety_eval: 7 rules (guarantee, scarcity_fake, medical_claim, financial, regulatory, personal_data, urgency); 0..100 → safe/needs_review/blocked
- saudi_tone_eval: positive markers (هلا, لاحظت, يناسبك) vs negative (تحية طيبة وبعد, synergy, leverage); arabic_ratio bonus
- eval_pack: 5 curated cases with expected verdicts
- cost_tracker: per workflow/provider/task_type aggregation

Routers (6 new) — 30 endpoints
- /api/v1/security-curator/{demo, redact, inspect-diff, sanitize-output}
- /api/v1/growth-curator/{skills/inventory, messages/grade, messages/improve, messages/duplicates, missions/next, report/weekly, report/demo}
- /api/v1/meeting-intelligence/{brief, brief/demo, transcript/summarize, followup/draft, deal-risk}
- /api/v1/model-router/{providers, tasks, route, cost-class, usage/demo}
- /api/v1/connector-catalog/{catalog, summary, status, risks, {key}}
- /api/v1/agent-observability/{trace/build, safety/eval, tone/eval, evals/run}

Tests (6 new files, 76 tests)
- test_security_curator: 16 tests (PAT detect, key redact, env diff block, payload scan, trace mask)
- test_growth_curator: 16 tests (Arabic grade, risky phrases, dup detect, playbook scoring, mission recommend, weekly report)
- test_meeting_intelligence: 13 tests (transcript parse, brief sections, objection extract, followup drafts, deal risk)
- test_dealix_model_router: 11 tests (every task → ≥1 provider, KSA-region for high sensitivity, cost class, primary override)
- test_agent_observability: 12 tests (trace hashing, safety verdicts, tone scoring, eval pack)
- test_connector_catalog: 11 tests (≥12 connectors, every has risk/blocked actions, WA cold-send blocked, Moyasar card-storage blocked)

Docs (8 new + 1 updated)
- AGENT_SECURITY_CURATOR.md (Arabic)
- GROWTH_CURATOR_STRATEGY.md (Arabic)
- MEETING_INTELLIGENCE.md (Arabic)
- MODEL_PROVIDER_ROUTER.md (Arabic)
- CONNECTOR_CATALOG.md (Arabic)
- AGENT_OBSERVABILITY_EVALS.md (Arabic)
- PRIVATE_BETA_LAUNCH_TODAY.md (Arabic) — go-checklist + offer + risks
- DEMO_SCRIPT_12_MINUTES.md (Arabic) — minute-by-minute demo flow
- FIRST_20_OUTREACH_MESSAGES.md (Arabic) — 7 personas + 3 follow-ups, all under safety/tone evals
- DEALIX_100_PERCENT_LAUNCH_PLAN.md — added §34 Self-Improving Agent Platform + §35 Private Beta Launch

Landing
- landing/private-beta.html — Arabic RTL, dark theme, pricing, 11 demo endpoints, safety banner

Test results
- 76/76 new tests pass
- Full suite: 663 passed, 2 skipped (missing API keys, unrelated)
- 0 existing tests broken

Safety
- All 6 layers honor approval-first, draft-only, no-live-send
- Hash user/company IDs before any trace
- No secrets in logs/embeddings/traces (3-layer defense: redactor + sanitizer + firewall)
- Saudi tone eval rejects "تحية طيبة وبعد" + "synergy" auto-corporate language
- Safety eval blocks "ضمان 100%" + medical claims + fake urgency
- Connector Catalog: WhatsApp blocks cold-send, Moyasar blocks card storage, MCP requires allowlist

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 16:30:18 +03:00

3.7 KiB
Raw Blame History

Private Beta Launch — Today's Plan

القرار: ندشّن Private Beta اليوم، ليس Public Launch. العرض الأساسي: "10 فرص في 10 دقائق" + Pilot 7 أيام + Proof Pack.

1. العرض

Pilot 7 أيام: 499 ريال أو مجاني مقابل case study
- 10 فرص B2B مع why-now
- 10 رسائل عربية جاهزة
- contactability + سياسة عدم الإرسال البارد
- متابعة لمدة 7 أيام
- Proof Pack بعد الأسبوع

Paid Pilot 30 يوم: 1,500–3,000 ريال
Growth OS اشتراك شهري: 2,999 ريال

2. من نستهدف اليوم (أول 20)

  1. وكالات تسويق B2B سعودية.
  2. مستشارون نمو.
  3. شركات تدريب B2B.
  4. SaaS سعودية صغيرة-متوسطة.
  5. شركات عقار/خدمات لديها واتساب نشط.
  6. أصدقاء مؤسسين سعوديين.

3. Demo Flow (12 دقيقة)

راجع DEMO_SCRIPT_12_MINUTES.md.

4. شروط القبول للعميل

العميل المثالي للـPrivate Beta:

  • شركة سعودية أو خليجية B2B.
  • لديها ≥3 موظفين مبيعات أو نمو.
  • مرتاحة بالعربي + الإنجليزي.
  • مستعدة لإعطاء feedback أسبوعي.
  • تقبل أنه draft-first (لا live send افتراضياً).

5. ما يعمل الآن (Phase 1 ready)

  • /api/v1/personal-operator/daily-brief
  • /api/v1/growth-operator/missions
  • /api/v1/growth-operator/proof-pack/demo
  • /api/v1/intelligence/command-feed/demo
  • /api/v1/intelligence/missions + /missions/recommend
  • /api/v1/intelligence/simulate-opportunity
  • /api/v1/intelligence/board-brief/demo
  • /api/v1/platform/services/catalog
  • /api/v1/platform/inbox/feed
  • /api/v1/platform/proof-ledger/demo
  • /api/v1/security-curator/demo
  • /api/v1/growth-curator/report/demo
  • /api/v1/meeting-intelligence/brief/demo
  • /api/v1/connector-catalog/catalog

6. ما يبقى Draft فقط

  • WhatsApp send (live flag OFF).
  • Gmail send (live flag OFF).
  • Calendar insert (live flag OFF).
  • Moyasar charge (live flag OFF — invoice/link manual).
  • Social DMs.

7. المخاطر

  • WhatsApp: PDPL — لا cold بدون opt-in.
  • Gmail: SPF/DKIM/DMARC للـdomain.
  • Moyasar: live keys ممنوعة في staging.
  • Secrets: GitHub Push Protection + Patch Firewall + Trace Redactor.
  • Hallucinations: Saudi Tone + Safety evals قبل publish.

8. Go-Checklist قبل أول demo

  • CI أخضر (Dealix API CI).
  • pytest -q ≥663 passed.
  • Staging URL يستجيب على /health.
  • جميع env flags الـ*_ALLOW_LIVE_* = false.
  • secret_redactor وpatch_firewall يعملان.
  • Demo URL مفتوح على /api/v1/intelligence/command-feed/demo.
  • Demo URL مفتوح على /api/v1/growth-operator/proof-pack/demo.
  • رسالة DM 1 جاهزة (راجع FIRST_20_OUTREACH_MESSAGES.md).

9. Post-Demo Checklist

  • قائمة 5 demos مجدولة.
  • قائمة 3 pilots محتملين.
  • feedback مكتوب لكل demo.
  • Proof Pack template جاهز.
  • أول Moyasar invoice draft (إن وُجد عميل).

10. ما لا نفعله اليوم

  • لا public launch.
  • لا live WhatsApp send.
  • لا charges.
  • لا "نضمن نتائج".
  • لا scraping.
  • لا إصدار صحفي.

11. الخطوة التالية بعد أول 3 demos

  • استخراج الاعتراضات الموحدة → cards في command_feed.
  • معايرة الأسعار (هل 499 رخيص جداً؟).
  • اختيار vertical: تدريب أو وكالات أو SaaS.
  • تجهيز case study واحد على الأقل.